out.bib
@techreport{ANSI-79,
author = {{American National Standards Institute Inc.}},
title = {{American National Standard for Writing Abstracts}},
address = {New York},
number = {ANSI Z39.14 -- 1979},
year = 1979,
institution = {American National Standards Institute}
}
@inproceedings{alemany-EACL-03,
author = {{Alonso i Alemany}, Laura and {Fuentes Fort}, Maria},
title = {Integrating cohesion and coherence for Automatic
Summarization},
url = {http://www.aclweb.org/anthology/E/E03/E03-3002.pdf},
booktitle = {Proceedings of the 11th Meeting of the European
Chapter of the Association for Computational
Linguistics},
address = {Budapest, Hungary},
abstract = {This paper presents the integration of cohesive
properties of text with coherence relations, to
obtain an adequate representation of text for
automatic summarization. A summarizer based on
Lexical Chains is enchanced with rhetorical and
argumentative structure obtained via Discourse
Markers. When evaluated with newspaper corpus, this
integration yields only slight improvement in the
resulting summaries and cannot beat a dummy baseline
consisting of the first sentence in the
document. Nevertheless, we argue that this approach
relies on basic linguistic mechanisms and is
therefore genreindependent},
month = {April 12 -- 17},
year = 2003,
pages = {1 -- 8}
}
@article{baxendale-58,
author = {Baxendale, Phyllis B.},
title = {Man-made index for technical literature - an
experiment},
journal = {I.B.M. Journal of Research and Development},
number = 4,
volume = 2,
year = 1958,
pages = {354 -- 361}
}
@incollection{boguraev-99,
author = {Boguraev, Branimir and Kennedy, Christopher},
editor = {Mani, Inderjeet and Maybury, Mark T.},
publisher = {The MIT Press},
title = {Salience-based content characterisation of text
documents},
url = {http://www.ling.northwestern.edu/\~{
}kennedy/Docs/content-char\_abs.html},
booktitle = {Advances in Automated Text Summarization},
abstract = {Traditionally, the document summarisation task has
been tackled either as a natural language processing
problem, with an instantiated meaning template being
rendered into a coherent prose, or as a passage
extraction problem, where certain fragments
(typically sentences) of the source document are
deemed to be highly representative of its content,
and thus delivered as meaningful ``approximations''
of it. Balancing the conflicting requirements of
depth and accuracy of a summary, on the one hand,
and document and domain independence, on the other,
has proven a very hard problem. This paper describes
a novel approach to content characterisation of text
documents. It is domain- and genre-independent, by
virtue of not requiring an in-depth analysis of the
full meaning. At the same time, it remains closer to
the core meaning by choosing a different granularity
of its representations (phrasal expressions rather
than sentences or paragraphs), by exploiting a
notion of discourse contiguity and coherence for the
purposes of uniform coverage and context
maintenance, and by utilising a strong linguistic
notion of salience, as a more appropriate and
representative measure of a document's
``aboutness''.},
year = 1999,
pages = {99 -- 110}
}
@book{borko-75,
author = {Borko, Harold and Bernier, Charles L.},
publisher = {Academic Press, London},
year = 1975,
title = {Abstracting concepts and methods}
}
@phdthesis{bosma-phd-08,
author = {Bosma, Wauter Eduard},
school = {University of Twente},
title = {Discourse oriented summarization},
abstract = {The meaning of text appears to be tightly related to
intentions and circumstances. Context sensitivity of
meaning is addressed by theories of discourse
structure. Few attempts have been made to exploit
text organization in summarization. This thesis is
an exploration of what knowledge of discourse
structure can do for content selection as a subtask
of automatic summarization, and query-based
summarization in particular. Query-based
summarization is the task of answering an arbitrary
user query or question by using content from
potentially relevant sources. This thesis presents a
general framework for discourse oriented
summarization, relying on graphs to represent
semantic relations in discourse, and redundancy as a
special type of semantic relation. Semantic
relations occur on several levels of text analysis
(query-relevance, coherence, layout, etc.), and a
broad range of textual features may be required to
detect them. The graph-based framework facilitates
combining multiple features into an integrated
semantic model of the documents to
summarize. Recognizing redundancy and entailment
relations between text passages is particularly
important when a summary is generated of multiple
documents, e.g. to avoid including redundant content
in a summary. For this reason, I pay particular
attention to recognizing textual entailment. Within
this framework, a three-fold evaluation is performed
to evaluate different aspects of discourse oriented
summarization. The first is a user study, measuring
the effect on user appreciation of using a
particular type of knowledge for query-based
summarization. In this study, three presentation
strategies are compared: summarization using the
rhetorical structure of the source, a baseline
summarization method which uses the layout of the
source, and a baseline presentation method which
uses no summarization but just a concise answer to
the query. Results show that knowledge of the
rhetorical structure not only helps to provide the
necessary context for the user to verify that the
summary addresses the query adequately, but also to
increase the amount of relevant content. The second
evaluation is a comparison of implementations of the
graph-based framework which are capable of fully
automatic summarization. The two variables in the
experiment are the set of textual features used to
model the source and the algorithm used to search a
graph for relevant content. The features are based
on cosine similarity, and are realized as graph
representations of the source. The graph search
algorithms are inspired by existing algorithms in
summarization. The quality of summaries is measured
using the Rouge evaluation toolkit. The best
performer would have ranked first (Rouge-2) or
second (Rouge-SU4) if it had participated in the DUC
2005 query-based summarization challenge. The third
study is an evaluation in the context of the DUC
2006 summarization challenge, which includes
readability measurements as well as various
content-based evaluation metrics. The evaluated
automatic discourse oriented summarization system is
similar to the one described above, but uses
additional features, i.e. layout and textual
entailment. The system performed well on readability
at the cost of content-based scores which were well
below the scores of the highest ranking DUC 2006
participant. This indicates a trade-off between
readable, coherent content and useful content, an
issue yet to be explored. Previous research implies
that theories of text organization generalize well
to multimedia. This suggests that the discourse
oriented summarization framework applies to
summarizing multimedia as well, provided sufficient
knowledge of the organization of the (multimedia)
source documents is available. The last study in
this thesis is an investigation of the applicability
of structural relations in multimedia for generating
picture-illustrated summaries, by relating summary
content to picture-associated text (i.e. captions or
surrounding paragraphs). Results suggest that
captions are the more suitable annotation for
selecting appropriate pictures. Compared to manual
illustration, results of automatic pictures are
similar if the manual picture is mainly decorative.},
year = 2009
}
@article{brandow-IPM-95,
author = {Brandow, Ronald and Mitze, Karl and Rau, Lisa F.},
title = {Automatic condensation of electronic publications by
sentence selection},
url = {http://dx.doi.org/10.1016/0306-4573(95)00052-I},
journal = {Information Processing \& Management},
number = 5,
abstract = {As electronic information access becomes the norm,
and the variety of retrievable material increases,
automatic methods of summarizing or condensing text
will become critical. This paper describes a system
that performs domain-independent automatic
condensation of news from a large commercial news
service encompassing 41 different publications.
This system was evaluated against a system that
condensed the same articles using only the first
portion of the texts (the lead), up to the target
length of the summaries. Three lengths of articles
were evaluated for 250 documents by both systems,
totalling 1500 suitability judgements in all. The
outcome of perhaps the largest evaluation of human
vs machine summarization performed to date was
unexpected. The lead-based summaries outperformed
the "intelligent" summaries significantly, achieving
acceptability ratings of over 90\%, compared to
74.4\%. This paper briefly reviews the literature,
details the implications of these results, and
addresses the remaining hopes for content-based
summarization. We expect the results presented here
to be useful to other researchers currently
investigating the viability of summarization through
sentence selection heuristics.},
volume = 31,
year = 1995,
pages = {675 -- 685}
}
@inproceedings{brunn-DUC-01,
author = {Brunn, Meru and Chali, Yllias and Pinchak,
Christopher J.},
title = {Text Summarization Using Lexical Chains},
url = {http://www-nlpir.nist.gov/projects/duc/pubs/2001papers/lethbridge.pdf},
booktitle = {Proceedings of DUC2001 Conference},
address = {New Orleans, Louisiana, USA},
month = {September 13 -- 14},
year = 2001,
annote = {Available at:
http://www-nlpir.nist.gov/projects/duc/pubs/2001papers/lethbridge.pdf},
abstract = {Text summarization addresses both the problem of
selecting the most important portions of text and
the problem of generating coherent summaries. We
present in this paper the summarizer of the
University of Lethbridge at DUC 2001, which is based
on an efficient use of lexical chains.}
}
@book{cleveland-83,
author = {Cleveland, Donald B.},
publisher = {Libraries Unlimited, Inc},
year = 1983,
title = {Introduction to Indexing and Abstracting}
}
@book{collinson-71,
author = {Collinson, R.},
publisher = {American Bibliographical Center - Clio Press},
year = 1971,
title = {Abstracts and abstracting services}
}
@book{cremmins-96,
author = {Cremmins, Edward T.},
edition = {2nd},
publisher = {Arlington, Va. : Information Resources Press},
year = 1996,
title = {The Art of Abstracting}
}
@incollection{dejong-82,
author = {DeJong, G.},
editor = {Lehnert, W. G. and Ringle, M. H.},
publisher = {Hillsdale, NJ: Lawrence Erlbaum},
title = {An overview of the {FRUMP} system},
booktitle = {Strategies for natural language processing},
year = 1982,
pages = {149 -- 176}
}
@book{dijk-80,
author = {van Dijk, Teun A.},
publisher = {London : Longman},
year = 1980,
title = {Text and context : explorations in the semantics and
pragmatics of discourse}
}
@article{edmundson-ACM-69,
author = {Edmundson, H. P.},
title = {New methods in Automatic Extracting},
url = {http://courses.ischool.berkeley.edu/i256/f06/papers/edmonson69.pdf},
journal = {Journal of the Association for Computing Machinery},
number = 2,
abstract = {This paper describes new methods of automatically
extracting documents for screening purposes,
i.e. the computer selection of sentences having the
greatest potential for conveying to the reader the
substance of the document. While previous work has
focused on one component of sentence significance,
namely, the presence of high-frequency content words
(key words), the methods described here also treat
three additional components: pragmatic words (cue
words); title and heading words; and structural
indicators (sentence location). The research has
resulted in an operating system and a research
methodology. The extracting system is parameterized
to control and vary the influence of the above four
components. The research methodology includes
procedures for the compilation of the required
dictionaries, the setting of the control parameters,
and the comparative evaluation of the automatic
extracts with manually produced extracts. The
results indicate that the three newly proposed
components dominate the frequency component in the
production of better extracts.},
month = {April},
volume = 16,
year = 1969,
pages = {264 -- 285}
}
@phdthesis{elhadad-phd-06,
author = {Elhadad, Noémie},
school = {Columbia University},
title = {User-Sensitive Text Summarization: Application to
the Medical Domain},
url = {http://people.dbmi.columbia.edu/noemie/papers/thesis.pdf},
abstract = {In this thesis, we present a user-sensitive approach
to text summarization. One domain which would
highly benefit from tailoring summaries to both
individual and class-based user characteristics is
the medical domain, where physicians and patients
access similar information, each with their own
needs and abilities. Our framework is a medical
digital library for physicians and patients. We
describe a summarizer, which generates summaries of
findings in an input set of clinical studies. When a
physician is treating a specific patient, he’s
looking for information relevant to the patient’s
history and problems. The summarizer takes the
user’s interests into account and presents only the
findings pertaining to a user model, as approximated
by an existing patient record. The same synthesis of
information can also be of interest to the
patient. The summarizer predicts which medical terms
used in a text will be too technical for patients,
and augments it with appropriate definitions when
necessary. We adopt a generation-like architecture
for our summarizer. However, because our input is
textual and not semantic, new challenges arise. We
operate over a content representation hybrid between
full-semantic and extracted phrases. Our content
organization strategy is dynamic and
data-driven. This is in contrast to most summarizers
which use no explicit strategies to order
information extracted from several input
documents. The result is more readable, coherent
output. To generate the actual summary, the
summarizer makes use of aggregation and phrasal
generation. The result is a concise and fluent
summary. One key challenge when it comes to
adapting a text for a different audience is
identifying the bottleneck for reader comprehension.
We analyzed corpora of technical and lay medical
texts and qualified differences. We identified the
presence of difficult vocabulary as the major
obstacle to comprehension for lay readers. We
designed an unsupervised method to predict which
terms are incomprehensible for lay readers and
provide the user with appropriate definitions. Our
methods are grounded on corpus analyses and
feasibility studies conducted with physicians and
consumers of health information. To assess the value
of our work, we evaluated our summarizer both
intrinsically and extrinsically. Our task-based
evaluation conducted with physicians at the ICU
demonstrates that personalized summaries help
physicians access relevant information better than
generic summaries. Evaluation with lay readers shows
that our method to augment technical medical texts
improves readers’ comprehension significantly.},
year = 2006,
type = {Ph.D. Thesis}
}
@book{endres-niggemeyer-98a,
author = {Endres-Niggemeyer, Brigitte},
publisher = {Springer},
year = 1998,
title = {Summarizing information}
}
@inproceedings{goldstein-ANLP-00,
author = {Goldstein, Jade and Mittal, Vibhu O. and Carbonell,
Jamie and Kantrowitz, Mark},
editor = {Hahn, Udo and Lin, Chin-Yew and Mani, Inderjeet and
Radev, Dragomir R.},
title = {{Multi-Document Summarization by Sentence
Extraction}},
booktitle = {Proceedings of the Workshop on Automatic
Summarization at the 6th Applied Natural Language
Processing Conference and the 1st Conference of the
North American Chapter of the Association for
Computational Linguistics},
address = {Seattle, WA},
month = {April},
year = 2000,
abstract = {This paper discusses a text extraction approach to
multi-document summarization that builds on
single-document summarization methods by using
additional, available information about the document
set as a whole and the relationships between the
documents. Multi-document summarization differs from
single in that the issues of compression, speed,
redundancy and passage selection are critical in the
formation of useful summaries. Our approach
addresses these issues by using domain-independent
techniques based mainly on fast, statistical
processing, a metric for reducing redundancy and
maximizing diversity in the selected passages, and a
modular framework to allow easy parameterization for
different genres, corpora characteristics and user
requirements.}
}
@inproceedings{goldstein-SIGIR-99,
author = {Goldstein, Jade and Kantrowitz, Mark and Mittal,
Vibhu and Carbonell, Jaime},
title = {Summarizing Text Documents: Sentence Selection and
Evaluation Metrics},
url = {http://citeseer.ist.psu.edu/goldstein99summarizing.html},
booktitle = {Proceedings of the 22nd Annual International ACM
SIGIR Conference on Research and Development in
Information Retrieval},
address = {Berkeley, California},
abstract = {Human-quality text summarization systems are
difficult to design, and even more difficult to
evaluate, in part because documents can differ along
several dimensions, such as length, writing style
and lexical usage. Nevertheless, certain cues can
often help suggest the selection of sentences for
inclusion in a summary. This paper presents our
analysis of news-article summaries generated by
sentence selection. Sentences are ranked for
potential inclusion in the summary using a weighted
combination of statistical and linguistic features.
The statistical features were adapted from standard
IR methods. The potential linguistic ones were
derived from an analysis of news-wire summaries. To
evaluate these features we use a normalized version
of precision-recall curves, with a baseline of
random sentence selection, as well as analyze the
properties of such a baseline. We illustrate our
discussions with empirical results showing the
importance of corpus-dependent baseline
summarization standards compression ratios and
carefully crafted long queries.},
month = {August, 15 -- 19},
year = 1999,
pages = {121 -- 128}
}
@incollection{graetz-85,
author = {Graetz, Naomi},
editor = {Ulign, J. M. and Pugh, A. K.},
publisher = {Leuven: Acco},
title = {Teaching {EFL} students to extract structural
information from abstracts},
url = {http://www.eric.ed.gov/ERICWebPortal/custom/portlets/recordDetails/detailmini.jsp?_nfpb=true&_&ERICExtSearch_SearchValue_0=ED224327&ERICExtSearch_SearchType_0=no&accno=ED224327},
booktitle = {Reading for Professional Purposes: Methods and
Materials in Teaching Languages},
abstract = {A brief narrative description of the journal
article, document, or resource.The benefits for
students of English as a second language of reading
abstracts are considered, and the functions and
types of abstracts are reviewed. In addition, the
results of a survey of Ben Gurion University
(Israel) lecturers regarding their reading habits
and use of abstracts are briefly addressed. It is
suggested that when abstracts are reproduced
together with the article, they can be used in the
classroom as advanced organizers. For the abstract
that follows the structure of the article exactly,
two types of activities may be undertaken: asking
the student to find and outline the corresponding
sections in the article, and forcing the student to
read between the subtitles. An example of how to
break down the structure of an abstract and relate
it to the article is presented: Abstracts can also
be used in isolation as cohesive and coherent texts
in their own right. For instance, since abstracts
are short texts, several abstracts on related topics
can be studied in much less time than it would take
to read one entire article. In planning the
curriculum, it is proposed that abstracts can be
used on all levels. For the lower level class, short
or indicative types of abstracts can be used. For
the intermediate level, longer, informative types
are useful, and for the advanced levels, the
critical abstract is appropriate. Appended material
includes sample abstracts, information on the
organization of the abstract, classifications of
introductory and concluding lines, a list of
journals with abstracts, an example of an ideal
abstract, and results of the faculty attitude
questionnaire.},
year = 1985,
pages = {123--135}
}
@inproceedings{hasler-CL-03,
author = {Hasler, Laura and Or\u{a}san, Constantin and Mitkov,
Ruslan},
title = {Building better corpora for summarisation},
url = {http://clg.wlv.ac.uk/papers/hasler-CL-03.pdf},
booktitle = {Proceedings of Corpus Linguistics 2003},
address = {Lancaster, UK},
month = {March, 28 -- 31},
year = 2003,
pages = {309 -- 319}
}
@phdthesis{hasler-phd-07,
author = {Hasler, Laura},
school = {University of Wolverhampton, UK},
title = {From extracts to abstracts: Human summary production
operations for computer-aided summarisation},
url = {http://clg.wlv.ac.uk/papers/hasler-thesis.pdf},
abstract = {This thesis is concerned with the field of
computer-aided summarisation, which has emerged at
the confluence of the separate but related fields of
human and automatic summarisation. Due to the poor
quality of the readability and coherence of
automatically produced extracts, computer-aided
summarisation (CAS) is a viable working option to
fully automatic summarisation. CAS allows a human
summariser to post-edit automatically produced
extracts to improve their readability and
coherence. In order to best utilise the concept of
computer-aided summarisation, reliable ways of
improving the coherence and readability of extracts
when transforming them into abstracts must be
established. To achieve this, a corpus-based
analysis of the operations a human summariser
applies to extracts to transform them into abstracts
is presented. The corpus developed here is a corpus
of pairs of news texts annotated for important
information (i.e., human-produced extracts) and the
human-produced abstracts corresponding to these
extracts. The creation of this corpus simulates the
computer-aided summarisation process to enable a
reliable investigation into the operations used. A
detailed classification of human summary production
operations is proposed, with examples which
highlight the common linguistic realisations and
functions of the operations identified in the
corpus. The classification is then used as a basis
for guidelines which can be given to users of
computer-aided summarisation systems in order to
ensure that the summaries they produce are of a
consistently high quality. The human summary
production operations are applied to extracts using
the guidelines in order to evaluate them. Evaluation
is performed using a metric developed for Centering
Theory, a discourse theory of local coherence and
salience, which constitutes a new evaluation
method. This is appropriate because existing methods
of evaluating summaries are unsuitable. A set of
both automatic and human- produced extracts and
their corresponding abstracts are evaluated, and a
comparison is made with evaluations given by a human
judge. The evaluation shows that when the operations
are applied to extracts using the guidelines, there
is an improvement in the readability and coherence
of the resulting abstracts.},
year = 2007
}
@phdthesis{hirao-phd-02,
author = {Hirao, Tsutomu},
school = {Nara Institute of Science and Technology},
title = {A Study on Generic and User-focused Automatic
Summarization},
url = {http://cl.aist-nara.ac.jp/thesis/dthesis-hirao.pdf},
abstract = {Due to the rapid growth of the Internet and the
emergence of low-price and large-capacity storage
devices, the number of online documents is
exploding. This situation makes it difficult to find
and gather the information we really
need. Therefore, many researchers have been studying
technologies to overcome this difficulty. Examples
include Automatic Summarization, Information
Retrieval (IR), Information Extraction (IE), and
Question-Answering (QA). In recent years, Automatic
Text Summarization has attracted the attention of a
lot of researchers in this field. This technology
produces overviews that are easier and faster to
browse than the original documents. This thesis
discusses the following three topics in automatic
text summarization: 1. High performance "generic"
single-document summarization with many features
(Chapter 2). 2. "Generic" multi-document
summarization by extending the single-document
summarization method (Chapter 3). 3. "User-focused"
summarization as evidence of answer in
Question-Answering Systems (Chapter 4). Chapter 2
proposes a method of “generic” single-document
summarization based on Support Vector Machines. It
is known that integrating heterogeneous sentence
features is effective for summarization. However, we
cannot manually find optimal parameter values for
these features when many features are
available. Therefore, machine learning has attracted
attention in order to integrate heterogeneous
features effectively. However, most machine
learning methods overfit the training data when many
features are given. In order to solve this
difficulty, we employ Support Vector Machines, which
are robust even when the number of features is
large. Moreover, we do not know what the effective
features are. To address this problem, we analyze
the weights of features and clarify them. Chapter 3
proposes a "generic" multi-document summarization
method using Support Vector Machines. Multi-document
summarization is almost the same as single-document
summarization, except that we need to consider extra
features for the former. Therefore, we face the same
problem as in single-document summarization: how to
handle many relevant features. We expand the
singledocument summarization method based on Support
Vector Machines to multidocument summarization. It
is said that a summary from multi-documents has
redundancy, i.e., there are redundant
sentences. Therefore, we investigate the
effectiveness of Maximum Marginal Relevance (MMR)
which is one of the generally used methods for
minimizing redundancy. In Chapter 4, we propose a
"user-focused" summarization method, Question-
Biased Text Summarization (QBTS), which produces
evidence of the Question- Answering system’s
answer. Question-Answering systems output the exact
answer to a question not a document. By using QA
systems, we can reduce the time taken to select
information. However, QA system’s outputs, i.e.,
answers, are not always correct. Therefore, we
propose a summarization method which focuses on not
only the question, but also on prospective answers
to the question to justify the correctness of the QA
system’s answer.},
month = {September},
year = 2002
}
@incollection{hovy-handbook-03,
author = {Hovy, Eduard},
editor = {Mitkov, Ruslan},
publisher = {Oxford University Press},
title = {Text summarisation},
url = {http://www.isi.edu/natural-language/people/hovy/papers/05Handbook-Summ-hovy.pdf},
booktitle = {The Oxford Handbook of computational linguistics},
year = 2003,
pages = {583 -- 598}
}
@inproceedings{jing-SIGIR-99,
author = {Jing, Hongyan and McKeown, Kathleen R.},
title = {The Decomposition of Human-Written Summary
Sentences},
url = {http://www.cs.columbia.edu/~hjing/papers/decomposition.ps},
booktitle = {Proceedings of the 22nd International Conference on
Research and Development in Information Retrieval
(SIGIR'99)},
address = {University of Berkeley, CA},
abstract = {We define the problem of decomposing human-written
summary sentences and propose a novel Hidden Markov
Model solution to the problem. Human summarizers
often rely on cutting and pasting of the full
document to generate summaries. Decomposing a
human-written summary sentence requires determining:
(1) whether it is constructed by cutting and
pasting, (2) what components in the sentence come
from the original document, and (3) where in the
document the components come from. Solving the
decomposition problem can potentially lead to the
automatic acquisition of large corpora for
summarization. It also sheds light on the generation
of summary text by cutting and pasting. The
evaluation shows that the proposed decomposition
algorithm performs well.},
month = {August},
year = 1999,
pages = {129 -- 136}
}
@article{johnson-95,
author = {Johnson, Frances},
title = {Automatic abstracting research},
url = {http://www.emeraldinsight.com/10.1108/00242539510102574},
journal = {Library review},
number = 8,
abstract = {The prospect of automatically generating abstracts
has attracted researchers for some time, but the
promise of superseding the human effort has yet to
be realized. Surveys the approaches and techniques
developed with the view to showing why this is
so. Particular emphasis is placed on the
requirements for the production of abstracts, which
effectively serve their intended function, to show
the ways in which this has hampered research in the
past. Suggests that progress of automatic
abstracting research may come about via the
integration of some of the techniques into
computerized information retrieval systems. This
will allow researchers to shift the aim from
reproducing the conventional benefits of abstracts
to accentuating the advantages to users of
computerized representation of information in large
textual databases.},
volume = 44,
year = 1995,
pages = {28 - 36}
}
@inproceedings{knight-AAAI-00,
author = {Knight, Kevin and Marcu, Daniel},
title = {Statistics-Based Summarization -- Step One: Sentence
Compression},
url = {http://www.isi.edu/\~{
}marcu/papers/aaai-stat-sum-00.pdf},
booktitle = {Proceedings of the 17th National Conference on
Artificial Intelligence (AAAI)},
address = {Austin, Texas, USA},
abstract = {When humans produce summaries of documents, they do
not simply extract sentences and concatenate
them. Rather, they create new sentences that are
grammatical, that cohere with one another, and that
capture the most salient pieces of information in
the original document. Given that large collections
of text/abstract pairs are available online, it is
now possible to envision algorithms that are trained
to mimic this process. In this paper, we focus on
sentence compression, a simpler version of this
larger challenge. We aim to achieve two goals
simultaneously: our compressions should be
grammatical, and they should retain the most
important pieces of information. These two goals can
conflict. We devise both noisy-channel and
decision-tree approaches to the problem, and we
evaluate results against manual compressions and a
simple baseline.},
month = {July 30 -- August 3},
todopages = {???},
year = 2000,
pages = {703 -- 710}
}
@inproceedings{kupiec-SIGIR-95,
author = {Kupiec, Julian and Pederson, Jan and Chen, Francine},
title = {A trainable document summarizer},
url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.1161},
booktitle = {Proceedings of the 18th ACM/SIGIR Annual Conference
on Research and Development in Information
Retrieval},
address = {Seattle},
month = {July 09 -- 13},
year = 1995,
pages = {68 -- 73}
}
@book{lancaster-98,
author = {Lancaster, Frederick W.},
edition = {2nd},
publisher = {London: Library Association},
year = 1998,
title = {Indexing and abstracting in theory and practice}
}
@inproceedings{lin-ROUGE-03,
author = {Lin, Chin-Yew and Hovy, Eduard H.},
title = {Automatic evaluation of summaries using n-gram
co-occurrence},
url = {http://portal.acm.org/citation.cfm?id=1073465},
booktitle = {Proceedings of 2003 Language Technology Conference
(HLT-NAACL 2003)},
address = {Edmonton, Canada},
abstract = {Following the recent adoption by the machine
translation community of automatic evaluation using
the BLEU/NIST scoring process, we conduct an
in-depth study of a similar idea for evaluating
summaries. The results show that automatic
evaluation using unigram co-occurrences between
summary pairs correlates surprising well with human
evaluations, based on various statistical metrics;
while direct application of the BLEU evaluation
procedure does not always give good results.},
month = {May 27 -- June 1},
year = 2003,
pages = {71 -- 78}
}
@inproceedings{lin-WAS-04,
author = {Lin, Chin-Yew},
title = {{ROUGE: a Package for Automatic Evaluation of
Summaries}},
url = {http://www.aclweb.org/anthology-new/W/W04/W04-1013.pdf},
booktitle = {Proceedings of the Workshop on Text Summarization
Branches Out (WAS 2004)},
address = {Barcelona, Spain},
month = {July 25 - 26},
year = 2004,
abstract = {ROUGE stands for Recall-Oriented Understudy for
Gisting Evaluation. It includes measures to
automatically determine the quality of a summary by
comparing it to other (ideal) summaries created by
humans. The measures count the number of
overlapping units such as n-gram, word sequences,
and word pairs between the computer-generated
summary to be evaluated and the ideal summaries
created by humans. This paper introduces four
different ROUGE measures: ROUGE-N, ROUGE-L, ROUGE-W,
and ROUGE-S included in the ROUGE summarization
evaluation package and their evaluatio ns. Three of
them have been used in the Document Understanding
Conference (DUC) 2004, a large-scale summarization
evaluation sponsored by NIST.}
}
@article{luhn-IBMJ-58,
author = {Luhn, H. P.},
title = {The automatic creation of literature abstracts},
url = {http://courses.ischool.berkeley.edu/i256/f06/papers/luhn58.pdf},
journal = {IBM Journal of research and development},
number = 2,
abstract = {Excerpts of technical papers and magazine articles
that serve the purposes of conventional abstracts
have been created entirely by automatic means. In
the exploratory research described, the complete
text of an article in machine-readable form is
scanned by an IBM 704 data-processing machine and
analyzed in accordance with a standard
program. Statistical information derived from word
frequency and distribution is used by the machine to
compute a relative measure of significance, first
for individual words and then for sentences.
Sentences scoring highest in significance are
extracted and printed out to become the
"auto-abstract."},
volume = 2,
year = 1958,
pages = {159 -- 165}
}
@book{mani-01,
author = {Mani, Inderjeet},
publisher = {John Benjamins Publishing Company},
title = {Automatic Summarization},
series = {Natural Language Processing},
year = 2001
}
@book{mani-99,
editor = {Mani, Inderjeet and Maybury, Mark T.},
publisher = {MIT Press},
title = {Advances in automatic text summarisatio},
url = {http://mitpress.mit.edu/catalog/item/default.asp?ttype=2&tid=3943},
abstract = {With the rapid growth of the World Wide Web and
electronic information services, information is
becoming available on-line at an incredible
rate. One result is the oft-decried information
overload. No one has time to read everything, yet we
often have to make critical decisions based on what
we are able to assimilate. The technology of
automatic text summarization is becoming
indispensable for dealing with this problem. Text
summarization is the process of distilling the most
important information from a source to produce an
abridged version for a particular user or task.
Until now there has been no state-of-the-art
collection of the most important writings in
automatic text summarization. This book presents the
key developments in the field in an integrated
framework and suggests future research areas. The
book is organized into six sections: Classical
Approaches, Corpus-Based Approaches, Exploiting
Discourse Structure, Knowledge-Rich Approaches,
Evaluation Methods, and New Summarization Problem
Areas},
year = 1999
}
@inproceedings{mani-AAAI-98,
author = {Mani, Inderjeet and Bloedorn, Eric},
publisher = {MIT Press},
title = {Machine learning of generic and user-focused
summarization},
url = {http://www.aaai.org/Papers/AAAI/1998/AAAI98-116.pdf},
booktitle = {Proceedings of the Fifthteen National Conference on
Artificial Intelligence},
address = {Madison, Wisconsin},
abstract = {A key problem in text summarization is finding a
salience function which determines what information
in the source should be included in the
summary. This paper describes the use of machine
learning on a training corpus of documents and their
abstracts to discover salience functions which
describe what combination of features is optimal for
a given summarization task. The method addresses
both "generic" and user-focused summaries.},
year = 1998,
pages = {821 -- 826}
}
@article{mani-IR-99,
author = {Mani, Inderjeet and Bloedorn, Eric},
title = {Summarizing Similarities and Differences Among
Related Documents},
journal = {Information Retrieval},
number = {1-2},
abstract = {In many modern information retrieval applications, a
common problem which arises is the existence of
multiple documents covering similar information, as
in the case of multiple news stories about an event
or a sequence of events. A particular challenge for
text summarization is to be able to summarize the
similarities and differences in information content
among these documents. The approach described here
exploits the results of recent progress in
information extraction to represent salient units of
text and their relationships. By exploiting
meaningful relations between units based on an
analysis of text cohesion and the context in which
the comparison is desired, the summarizer can
pinpoint similarities and differences, and align
text segments. In evaluation experiments, these
techniques for exploiting cohesion relations result
in summaries which (i) help users more quickly
complete a retrieval task (ii) result in improved
alignment accuracy over baselines, and (iii) improve
identification of topic-relevant similarities and
differences.},
month = {May},
volume = 1,
year = 1999,
pages = {35-67}
}
@techreport{mani-SUMMAC-98,
author = {Mani, Inderjeet and Firmin, Therese and House, David
and Chrzanowski, Michael and Klein, Gary and
Hirshman, Lynette and Sundheim, Beth and Obrst, Leo},
title = {The {TIPSTER SUMMAC} Text Summarisation Evaluation:
Final Report},
url = {\url{http://www.itl.nist.gov/iaui/894.02/related_projects/tipster_summac/index.html}},
abstract = {In May 1998, the U.S. government completed the
TIPSTER Text Summarization Evaluation (SUMMAC),
which was the first large-scale,
developer-independent evaluation of automatic text
summarization systems. Two main extrinsic evaluation
tasks were defined, based on activities typically
carried out by information analysts in the
U.S. Government. In the adhoc task, the focus was on
indicative summaries which were tailored to a
particular topic. In the categorization task, the
evaluation sought to find out whether a generic
summary could effectively present enough information
to allow an analyst to quickly and correctly
categorize a document. The final, question-answering
task involved an intrinsic evaluation where a
topic-related summary for a document was evaluated
in terms of its "informativeness", namely, the
degree to which it contained answers found in the
source document to a set of topic-related questions.
SUMMAC has established definitively in a large-scale
evaluation that automatic text summarization is very
effective in relevance assessment tasks. Summaries
at relatively low compression rates (17\% for adhoc,
10\% for categorization) allowed for relevance
assessment almost as accurate as with full-text (5\%
degradation in F-score for adhoc and 14\%
degradation for categorization, both degradations
not being statistically significant), while reducing
decision-making time by 40\% (categorization) and
50\% (adhoc). In the question-answering task,
automatic methods for measuring informativeness of
topic-related summaries were introduced; the
systems' scores using the automatic methods were
found to correlate positively with informativeness
scores rendered by human judges. The evaluation
methods used in the SUMMAC evaluation are of
intrinsic interest to both summarization evaluation
as well as evaluation of other "output-related" NLP
technologies, where there may be many potentially
acceptable outputs, with no automatic way to compare
them.},
number = {MTR 98W0000138},
year = 1998,
institution = {The MITRE Corporation}
}
@book{marcu-00,
author = {Marcu, Daniel},
publisher = {The MIT Press},
year = 2000,
title = {The theory and practice of discourse parsing and
summarisation}
}
@inproceedings{marcu-AAAI-99,
author = {Marcu, Daniel},
title = {The automatic construction of large-scale corpora
for summarization research},
url = {http://portal.acm.org/citation.cfm?id=312624.312668},
booktitle = {The 22nd International ACM SIGIR Conference on
Research and Development in Information Retrieval
(SIGIR'99)},
address = {Berkeley, CA},
abstract = {Summarization research is notorious for its lack of
adequate corpora: today, there exist only a few
small collections of texts whose units have been
manually annotated for textual importance. Given the
cost and tediousness of the annotation process, it
is very unlikely that we will ever manually annotate
for textual importance sufficiently large corpora of
texts. To circumvent this problem, we have developed
an algorithm that constructs such corpora
automatically. Our algorithm takes as input an
hAbstract, Texti tuple and generates the
corresponding Extract, i.e., the set of clauses
(sentences) in the Text that were used to write the
Abstract. The performance of the algorithm is shown
to be close to that of humans by means of an
empirical experiment. The experiment also suggests
extraction strategies that could improve the
performance of automatic summarization systems.},
month = {August 15 -- 19},
year = 1999,
pages = {137-144}
}
@phdthesis{marcu-phd-97,
author = {Marcu, Daniel},
school = {Department of Computer Science, University of
Toronto, Toronto, Canada},
title = {The Rhetorical Parsing, Summarization and Generation
of Natural Language Texts},
url = {http://www.isi.edu/~marcu/papers/phd-thesis.ps.gz},
year = 1997
}
@inproceedings{miike-SIGIR-94,
author = {Miike, Seiji and Itoh, Etsuo and Ono, Kenji and
Sumita, Kazuo},
publisher = {ACM/Springer},
title = {A Full-Text Retrieval System with a Dynamic Abstract
Generation Function},
url = {http://portal.acm.org/citation.cfm?id=188550},
booktitle = {Proceedings of the 17th ACM SIGIR conference},
address = {Dublin, Ireland},
abstract = {We have developed a Japanese full-text retrieval
system named BREVIDOC that enables the user to
specify an area within a text for abstraction and to
control the volume of the abstract
interactively. This system analyzes a document
structure using linguistic knowledge only and thus
is domain-independent. In its text structure
analysis, the system determines relations among
paragraphs and sentences, based on linguistic clues
such as connective, anaphoric expressions, and
idiomatic expressions. The system analyzes and
stores the text structure in advance so that it can
generate an abstract in real time by selecting
sentences according to relative importance of
rhetorical relations among the sentences. The
retrieval system works on an engineering
workstation.},
month = {3-6 July},
year = 1994,
pages = {152 -- 161}
}
@inproceedings{minel-ISTS-97,
author = {Minel, Jean-Luc and Nugier, Sylvaine and Piat,
Gerald},
title = {How to appreciate the quality of automatic text
summarization?},
url = {http://www.aclweb.org/anthology-new/W/W97/W97-0705.pdf},
booktitle = {Proceedings of the ACL'97/EACL'97 Workshop on
Intelligent Scallable Text Summarization},
address = {Madrid, Spain},
abstract = {For the SERAPHIN project, we set up two assessment
protocols in order to be able to more accurately
assess the quality of abstracts - the FAN protocol
and the MLUCE protocol, for which we provide the
results. The FAN protocol assesses the legibility
of an abstract, independently from the source text
The MLUCE protocol ls designed to allow users of
automatic abstracts to assess their quality. These
protocols were applied to a corpus of 27 texts which
varied in length from between three and twelve
pages. These texts were randomly chosen from EDF
archives. They include both scientific and general
press articles, extracts from books, and internal
EDP notes. The results of the FAN protocol
demonstrate the difficulty of using surface
linguistic indicators to assess the quality of an
abstract, the results of the MLUCE protocol
illustrate the importance of user expectations.},
month = {July 11},
year = 1997,
pages = {25 -- 30}
}
@book{moens-00,
author = {Moens, Marie-Francine},
publisher = {Kluwer Academic Publishers},
year = 2000,
title = {Automatic Indexing and Abstracting of Document
Texts}
}
@article{morris-ISR-92,
author = {Morris, Andrew H. and Kasper, George M. and Adams,
Dennis A.},
title = {The effect and limitations of automatic text
condensing on reading comprehension performance},
journal = {Information Systems Research},
number = 1,
volume = 3,
year = 1992,
pages = {17 -- 35}
}
@phdthesis{nomoto-phd-04,
author = {Nomoto, Tadashi},
school = {Nara Institute of Science and Technology},
title = {Machine Learning Approaches in Rhetorical Parsing
and Open-domain Text Summarization},
url = {http://cl.aist-nara.ac.jp/thesis/dthesis-nomoto.pdf},
abstract = {The present thesis primarily concerns the use of
machine learning for rhetorical parsing and
open-domain text summarization. Chapter 1 sets a
general backdrop on text summarization and its
subfield, rhetorical parsing, and defines the area
of investigation. Chapters 2 through 9 form the core
of the thesis, developing each theme in great depth,
for which we will give a brief overview
below. (Throughout the thesis, we talk about
extractive summarization, meaning that we create a
summary by putting together bits and pieces,
usually, sentences extracted from text.) In
chapters 2 through 5, we motivate and develop a
novel approach to rhetorical parsing based on the
decision tree (DT) learning, which one could adapt
for any genre and language given a training corpus.
(Unless stated otherwise, DT here and below means
Quinlan’s C4.5 with default settings.) An important
goal of rhetorical parsing is to recover rhetorical
structure of text for potential use with text
summarization. Performance of our approach is
evaluated using an hand-annotated corpus of Japanese
newspaper articles. Also some problems with
annotating with rhetorical information such as the
variability of human judgments on labeling are noted
and discussed. In addition some refinements are
made on the DT learning itself by appeal to the
minimum description length principle (MDL) and
active learning. Evaluation is done using the same
data as above. We also look into how a DT harnessed
with MDL (DT/MDL), compares in performance with
AdaBoosted DT. Due to poor results with the
linguistically motivated paradigm that previous
chapters represent, we turn an eye on non-linguistic
approaches to summarization. Chapter 6 explores an
unsupervised paradigm for text summarization. We
develop there what we call the diversity based
summarization or DBS, which consists in the K-means
clustering (again extended with MDL) and a simple
sentence ranking scheme. A new evaluative scheme for
summarization (which we call the information-centric
approach to evaluation of summaries, or ICE) is also
proposed with an eye to providing an objective
assessment of the utility of machine generated
summaries. Evaluation is conducted using a publicly
available corpus known as BMIR-J2. Then we proceed
to the issue of modeling human created summaries in
the DBS paradigm. We compare performance of DBS and
DT- (and DT/MDL-) based summarizers trained on a
human-annotated corpus. Curiously enough, it is
found that DBS closely rivals and sometimes
outperforms DT- and DT/MDL- based summarizers –
which we collectively call ‘DT(/MDL)’ here – when
tested on those annotations which judges tend to
disagree on, but falls behind DT(/MDL) on
annotations for which there is a strong agreement
among judges. The result suggests that there are
some useful, i.e., DT-learnable, patterns in
annotations for which people have a more or less
same idea about what they should be like. While
DT(/MDL) is apparently able to exploit patterns to
its advantage, DBS, being unsupervised, is not able
to perform as well as when it is run on annotations
with varying judgments. Which however points to an
integration of DT(/MDL) with DBS as a possible
alternative to DBS as the combine should then be
able to take into account the regularity as well as
variability of human summaries, an issue that
engages us in subsequent chapters, where we consider
other variations of DT. We argue that taking into
account both properties indeed leads to a better
performing summarizer. Finally, we look at curious
regularities in the way people vote for summary
sentences when asked to pick up those they consider
important or summary-worthy. Texts from a news wire
domain typically show that initially occurring
sentences are popularly voted or preferred for
summary sentences while those occurring later in
text decidedly get less popular. Texts from a column
domain, on the other hand, exhibit a somewhat
different pattern, showing that sentences occurring
towards the end are as much favored by people as
those occurring text-initially. We argue that the
distribution of votes for summary sentences, which
we call ‘DOV,’ has some shape specific to a domain,
and propose a particular approach that directly
exploits DOVs by way of Bayesian modeling. We show
that the Bayesian model provides a significant
leverage over approaches based on pattern
classifiers such as C4.5, Adtree, Kstar, Naive
Bayes, etc.},
month = {December},
year = 2004
}
@inproceedings{oka-NAACL-00,
author = {Oka, Mamiko and Ueda, Yoshihiro},
title = {Evaluation of Phrase-Representation Summarization
Based on Information Retrieval Task},
url = {http://www.aclweb.org/anthology/W/W00/W00-0407.pdf},
booktitle = {NAACL-ANLP 2000 Workshop on Automatic Summarization},
address = {Seattle, Washington},
abstract = {We have developed an improved task-based evaluation
method of summarization, the accuracy of which is
increased by specifying the details of the task
including background stories, and by assigning ten
subjects per summary sample. The method also serves
precision/recall pairs for a variety of situations
by introducing multiple levels of relevance
assessment. The method is applied to prove
phrase-represented summary is most effective to
select relevant documents from information retrieval
results.},
month = {April 30},
year = 2000,
pages = {59 -- 68}
}
@inproceedings{okumura-TS-03,
author = {Okumura, Manabu and Fukusima, Takahiro and Nanba,
Hidetsugu},
title = {{Text Summarization Challenge 2: Text Summarization
Evaluation at NTCIR Workshop 3}},
url = {http://acl.ldc.upenn.edu/W/W03/W03-0507.pdf},
booktitle = {Proceeding of the HLT-NAACL 2003 Workshop on Text
Summarization},
address = {Edmonton, Alberta, Canada},
abstract = {We describe the outline of Text Summarization
Challenge 2 (TSC2 hereafter), a sequel text
summarization evaluation conducted as one of the
tasks at the NTCIR Workshop 3. First, we describe
briefly the previous evaluation, Text Summarization
Challenge (TSC1) as introduction to TSC2. Then we
explain TSC2 including the participants, the two
tasks in TSC2, data used, evaluation methods for
each task, and brief report on the results.},
month = {May 31 -- June 1},
year = 2003,
pages = {49 -- 56}
}
@phdthesis{orasan-PHD-06,
author = {Or\u{a}san, Constantin},
school = {University of Wolverhampton},
title = {Comparative evaluation of modular automatic
summarisation systems using {CAST}},
url = {http://www.wlv.ac.uk/~in6093/papers/PhD/Thesis.pdf},
abstract = {The information overload faced by today's society
poses great challenges to researchers who want to
find a relevant piece of information. Automatic
summarisation is a field of computational
linguistics which can help humans to deal with this
information overload by automatically extracting the
gist of documents. This thesis attempts to gain
insights into the automatic summarisation field from
several different angles. First, it performs
qualitative, quantitative and comparative
evaluations of different automatic summarisation
methods. These summarisation methods are built
around a term-based summariser which is then
augmented with additional linguistic information
which includes lexical, semantic and discourse
information. On the basis of these evaluations, it
was noticed that the choice of modules which provide
low-level linguistic information (e.g. morphological
processors) does not influence the results
significantly, but higher level linguistic
information, such as anaphora resolution and shallow
information about discourse structure, leads to
significant improvements of the summaries. In order
to have a comprehensive view of how good summaries
produced by a given method are, the evaluation
performed in this thesis measures both the
informativeness of the summaries produced and the
quality of their discourse structure. Moreover, a
method which determines the upper limit for
informativeness is proposed to demonstrate the
limits of extraction techniques. Comparison between
the informativeness and the quality of discourse
reveals no correlation between them. A third
direction pursued in this research is to replace
conventional iterative extraction methods, which
extract one sentence at a time without considering
the rest of the sentences in the summary, with more
holistic ones, where the decision to extract a
sentence is determined not only by the content of a
sentence, but also by the rest of the sentences
extracted. To this end, a genetic algorithm which
encodes the whole summary is implemented and is
shown to produce better summaries than its iterative
equivalent.},
year = 2006
}
@inproceedings{orasan-RANLP-07,
author = {Or\u{a}san, Constantin and Hasler, Laura},
title = {Computer-Aided Summarisation: how much does it
really help?},
url = {http://clg.wlv.ac.uk/papers/orasan-hasler-RANLP-07.pdf},
booktitle = {Proceedings of Recent Advances in Natural Language
Processing (RANLP 2007)},
address = {Borovets, Bulgaria},
abstract = {Computer-aided summarisation is a technology
developed as a complement to automatic
summarisation, which produces high quality summaries
with less effort. To achieve this, a user-friendly
environment which incorporates several well-known
summarisation methods has been developed. This
paper presents the main features of the
computer-aided summarisation environment and
evaluates the usefulness of the developed
tool. Experiments showed that it is possible to
reduce the time necessary to produce the summary by
about 20% without any degradation in the summary's
quality.},
month = {September 27-29},
year = 2007,
pages = {437 -- 441}
}
@inproceedings{osborne-ACL-02,
author = {Osborne, Miles},
title = {Using maximum entropy for sentence extraction},
url = {http://portal.acm.org/citation.cfm?id=1118163},
booktitle = {Proceedings of ACL 2002 Workshop on Automatic
Summarization},
address = {Philadelphia, Pennsylvania},
abstract = {A maximum entropy classifier can be used to extract
sentences from documents. Experiments using
technical documents show that such a classifier
tends to treat features in a categorical
manner. This results in performance that is worse
than when extracting sentences using a naive Bayes
classifier. Addition of an optimised prior to the
maximum entropy classifier improves performance over
and above that of naive Bayes (even when naive Bayes
is also extended with a similar prior). Further
experiments show that, should we have at our
disposal extremely informative features, then
maximum entropy is able to yield excellent
results. Naive Bayes, in contrast, cannot exploit
these features and so fundamentally limits sentence
extraction performance.},
month = {July},
year = 2002,
pages = {1 -- 8}
}
@incollection{paice-81,
author = {Paice, Chris D.},
editor = {Oddy, R. N. and Rijsbergen, C. J. and Williams,
P. W.},
publisher = {London: Butterworths},
title = {The automatic generation of literature abstracts: an
approach based on the identification of
self-indicating phrases},
url = {http://portal.acm.org/citation.cfm?id=636680},
booktitle = {Information Retrieval Research},
address = {Kent, UK},
year = 1981,
pages = {172 -- 191}
}
@inproceedings{radev-LREC-04,
author = {Radev, Dragomir and Otterbacher, Jahna and Zhang,
Zhu},
title = {{CSTBank: A Corpus for the Study of Cross-document
Structural Relationship}},
url = {\url{http://clair.si.umich.edu/~radev/papers/lrec-cst04.pdf}},
booktitle = {Proceedings of Language Resources and Evaluation
Conference (LREC 2004)},
address = {Lisbon, Portugal},
year = 2004,
abstract = {Clusters of multiple news stories related to the
same topic exhibit a number of interesting
properties. For example, when documents have been
published at various points in time or by different
authors or news agencies, one finds many instances
of paraphrasing,information overlap and even
contradiction. The current paper presents the
Cross-document Structure Theory (CST) Bank, a
collection of multi-document clusters in which pairs
of sentences from different documents have been
annotated for cross-document structure theory
relationships. We will describe how we built the
corpus, including our method for reducing the number
of sentence pairs to be annotated by our hired
judges, using lexical similarity measures. Finally,
we will describe how CST and the CST Bank can be
applied to different research areas such as
multi-document summarization.}
}
@inproceedings{radev-NAACL-00,
author = {Radev, Dragomir R. and Jing, Hongyan and
Budzikowska, Malgorzata},
title = {Centroid-based summarization of multiple documents:
sentence extraction, utility-based evaluation and
user studies},
url = {http://aclweb.org/anthology-new/W/W00/W00-0403.pdf},
booktitle = {Proceedings of the NAACL/ANLP Workshop on Automatic
Summarization},
address = {Seattle, WA, USA},
abstract = {We present a multi-document summarizer, called MEAD,
which generates summaries using cluster centroids
produced by a topic detection and tracking
system. We also describe two new techniques, based
on sentence utility and subsumption, which we have
applied to the evaluation of both single and
multiple document summaries. Finally, we describe
two user studies that test our models of
multi-document summarization.},
month = {30 April},
year = 2000,
pages = {21 -- 29}
}
@inproceedings{saggion-NAACL-00,
author = {Saggion, Horacio and Lapalme, Guy},
title = {Concept Identification and Presentation in the
Context of Technical Text Summarization},
url = {http://aclweb.org/anthology-new/W/W00/W00-0401.pdf},
booktitle = {NAACL-ANLP 2000 Workshop on Automatic Summarization},
address = {Seattle, Washington},
abstract = {We describe a method of text summarization that
produces indicative-informative abstracts for
technical papers. The abstracts are generated by a
process of conceptual identification, topic
extraction and re-generation. We have carried out
an evaluation to assess indicativeness and text
acceptability relying on human judgment. The results
so far indicate good performance in both tasks when
compared with other summarization technologies.},
month = {April 30},
year = 2000,
pages = {1 -- 10}
}
@article{salton-IPM-97,
author = {Salton, Gerard and Singhal, Amit and Mitra, Mandar
and Buckley, Chris},
title = {Automatic text structuring and summarization},
url = {http://dx.doi.org/10.1016/S0306-4573(96)00062-3},
journal = {Information Processing and Management},
number = 3,
abstract = {In recent years, information retrieval techniques
have been used for automatic generation of semantic
hypertext links. This study applies the ideas from
the automatic link generation research to attack
another important problem in text processing
automatic text summarization. An automatic "general
purpose" text summarization tool would be of immense
utility in this age of information overload. Using
the techniques used (by most automatic hypertext
link generation algorithms) for inter-document link
generation, we generate intra-document links between
passages of a document. Based on the intra-document
linkage pattern of a text, we characterize the
structure of the text. We apply the knowledge of
text structure to do automatic text summarization by
passage extraction. We evaluate a set of fifty
summaries generated using our techniques by
comparing them to paragraph extracts constructed by
humans. The automatic summarization methods perform
well, especially in view of the fact that the
summaries generated by two humans for the same
article are surprisingly dissimilar.},
volume = 33,
year = 1997,
pages = {193 -- 207}
}
@article{silber-CL-02,
author = {Silber, H. Gregory and McCoy, Kathleen F.},
title = {Efficiently Computed Lexical Chains As an
Intermediate Representation for Automatic Text
Summarization},
url = {http://www.aclweb.org/anthology/J02-4004.pdf},
journal = {Computational linguistics},
number = 4,
abstract = {While automatic text summarization is an area that
has received a great deal of attention in recent
research, the problem of efficiency in this task has
not been frequently addressed. When the size and
quantity of documents available on the Internet and
from other sources are considered, the need for a
highly efficient tool that produces usable summaries
is clear. We present a linear-time algorithm for
lexical chain computation. The algorithm makes
lexical chains a computationally feasible candidate
as an intermediate representation for automatic text
summarization. A method for evaluating lexical
chains as an intermediate step in summarization is
also presented and carried out. Such an evaluation
was heretofore not possible because of the
computational complexity of previous lexical chains
algorithms.},
volume = 28,
year = 2002,
pages = {487 -- 496}
}
@inproceedings{silber-IUI-00,
author = {Silber, H. Gregory and McCoy, Kathleen F.},
title = {Efficient text summarization using lexical chains},
url = {http://web.media.mit.edu/~lieber/IUI/Silber/Silber.pdf},
abstract = {The rapid growth of the Internet has resulted in
enormous amounts of information that has become more
difficult to access efficiently. Internet users
require tools to help manage this vast quantity of
information. The primary goal of this research is to
create an efficient and effective tool that is able
to summarize large documents quickly. This research
presents a linear time algorithm for calculating
lexical chains which is a method of capturing the
"aboutness" of a document. This method is compared
to previous, less efficient methods of lexical chain
extraction. We also provide alternative methods for
extracting and scoring lexical chains. We show that
our method provides similar results to previous
research, but is substantially more efficient. This
efficiency is necessary in Internet search
applications where many large documents may need to
be summarized at once, and where the response time
to the end user is extremely important.},
address = {New Orleans, Louisiana, United States},
pages = {252--255},
year = 2000,
booktitle = {Proceedings of the 5th International Conference on
Intelligent User Interfaces}
}
@incollection{sparck-jones-99,
author = {{Sparck Jones}, Karen},
editor = {Mani, Inderjeet and Maybury, Mark T.},
chapter = 1,
publisher = {The MIT Press},
title = {Automatic summarizing: factors and directions},
booktitle = {Advances in automatic text summarization},
abstract = {This position paper suggests that progress with
automatic summarising demands a better research
methodology and a carefully focussed research
strategy. In order to develop e ective procedures it
is necessary to identify and respond to the context
factors, i.e. input, purpose, and output factors,
that bear on summarising and its evaluation. The
paper analyses and illustrates these factors and
their implications for evaluation. It then argues
that this analysis, together with the state of the
art and the intrinsic dffculty of summarising, imply
a nearer-term strategy concentrating on shallow, but
not surface, text analysis and on indicative
summarising. This is illustrated with current work,
from which a potentially productive research
programme can be developed.},
year = 1999,
pages = {1 -- 12}
}
@article{sparck-jones-IPM-07,
author = {{Sparck Jones}, Karen},
title = {Automatic summarising: The state of the art},
url = {http://dx.doi.org/10.1016/j.ipm.2007.03.009},
journal = {Information Processing and Management},
abstract = {This paper reviews research on automatic summarising
in the last decade. This work has grown, stimulated
by technology and by evaluation programmes. The
paper uses several frameworks to organise the
review, for summarising itself, for the factors
affecting summarising, for systems, and for
evaluation. The review examines the evaluation
strategies applied to summarising, the issues they
raise, and the major programmes. It considers the
input, purpose and output factors investigated in
recent summarising research, and discusses the
classes of strategy, extractive and non-extractive,
that have been explored, illustrating the range of
systems built. The conclusions drawn are that
automatic summarisation has made valuable progress,
with useful applications, better evaluation, and
more task understanding. But summarising systems are
still poorly motivated in relation to the factors
affecting them, and evaluation needs taking much
further to engage with the purposes summaries are
intended to serve and the contexts in which they are
used.},
volume = 43,
year = 2007,
pages = {1449 -- 1481}
}
@article{teufel-CL-02,
author = {Teufel, Simone and Moens, Marc},
title = {Summarizing Scientific Articles: Experiments with
Relevance and Rhetorical Status},
url = {http://www.aclweb.org/anthology/J/J02/J02-4002.pdf},
journal = {Computational linguistics},
number = 4,
abstract = {In this article we propose a strategy for the
summarization of scientific articles that
concentrates on the rhetorical status of statements
in an article: Material for summaries is selected in
such a way that summaries can highlight the new
contribution of the source article and situate it
with respect to earlier work. We provide a gold
standard for summaries of this kind consisting of a
substantial corpus of conference articles in
computational linguistics annotated with human
judgments of the rhetorical status and relevance of
each sentence in the articles. We present several
experiments measuring our judges' agreement on these
annotations. We also present an algorithm that, on
the basis of the annotated training material,
selects content from unseen articles and classifies
it into a fixed set of seven rhetorical
categories. The output of this extraction and
classification system can be viewed as a
single-document},
volume = 28,
year = 2002,
pages = {409 -- 445}
}
@inproceedings{teufel-ISTS-97,
author = {Teufel, Simone and Moens, Marc},
title = {Sentence extraction as a classification task},
url = {http://www.aclweb.org/anthology/W/W97/W97-0710.pdf},
booktitle = {Proceedings of the ACL'97/EACL'97 Workshop on
Intelligent Scallable Text Summarization},
address = {Madrid, Spain},
abstract = {A useful first step in document summarisation is the
selection of a small number of `meaningful'
sentences from a larger text. Kupiec et al. (1995)
describe this as a classification task: on the basis
of a corpus of technical papers with summaries
written by professional abstractors, their system
identifies those sentences in the text which also
occur in the summary, and then acquires a model of
the `abstract-worthiness' of a sentence as a
combination of a limited number of properties of
that sentence. We report on a replication of this
experiment with different data: summaries for our
documents were not written by professional
abstractors, but by the authors themselves. This
produced fewer alignable sentences to train on. We
use alternative `meaningful' sentences (selected by
a human judge) as training and evaluation material,
because this has advantages for the subsequent
automatic generation of more flexible abstracts. We
quantitatively compare the two different strategies
for training and evaluation (vi\ ahgnment vs human
judgement), we also discusses qualitative
differences and consequences for the generatlon of
abstracts.},
month = {July 11},
year = 1997,
pages = {58 -- 59}
}
@phdthesis{teufel-phd-99,
author = {Teufel, Simone},
school = {University of Edinburgh},
title = {{Argumentative Zoning: Information Extraction from
Scientific Text}},
url = {http://www.cl.cam.ac.uk/users/sht25/az.html},
abstract = {We present a new type of analysis for scientific
text which we call Argumentative Zoning. We
demonstrate that this type of text analysis can be
used for generating user-tailored and task-tailored
summaries and for performing more informative
citation analyses. We also demonstrate that our
type of analysis can be applied to unrestricted
text, both automatically and by humans. The corpus
we use for the analysis (80 conference papers in
computational linguistics) is a difficult test bed;
it shows great variation with respect to subdomain,
writing style, register and linguistic
expression. We present reliability studies which we
performed on this corpus and for which we use two
unrelated trained annotators. The definition of our
seven categories (argumentative zones) is not
specific to the domain, only to the text type; it is
based on the typical argumentation to be found in
scientific articles. It reflects the attribution of
intellectual ownership in scientific articles,
expressions of authors' stance towards other work,
and typical statements about problem-solving
processes. On the basis of sentential features, we
use two statistical models (a Naive Bayesian model
and an ngram model operating over sentences) to
estimate a sentence's argumentative status, taking
the hand-annotated corpus as training material. An
alternative, symbolic system uses the features in a
rule-based way. The general working hypothesis of
this thesis is that empirical discourse studies can
contribute to practical document management
problems: the analysis of a significant amount of
naturally occurring text is essential for discourse
linguistic theories, and the application of a robust
discourse and argumentation analysis can make text
understanding techniques for practical document
management more robust.},
year = 1999
}
@phdthesis{tucker-phd-99,
author = {Tucker, Richard},
school = {University of Cambridge},
title = {Automatic summarising and the {CLASP} system},
url = {http://www.cl.cam.ac.uk/techreports/UCAM-CL-TR-484.html},
abstract = {This dissertation discusses summarisers and
summarising in general, and presents CLASP, a new
summarising system that uses a shallow semantic
representation of the source text called a
"predication cohesion graph". Nodes in the graph
are "simple predications" corresponding to events,
states and entities mentioned in the text; edges
indicate related or similar nodes. Summary content
is chosen by selecting some of these predications
according to criteria of "importance",
"representativeness" and "cohesiveness". These
criteria are expressed as functions on the nodes of
a weighted graph. Summary text is produced either by
extracting whole sentences from the source text, or
by generating short, indicative "summary phrases"
from the selected predications. CLASP uses
linguistic processing but no domain knowledge, and
therefore does not restrict the subject matter of
the source text. It is intended to deal robustly
with complex texts that it cannot analyse completely
accurately or in full. Experiments in summarising
stories from the Wall Street Journal suggest there
may be a benefit in identifying important material
in a semantic representation rather than a surface
one, but that, despite the robustness of the source
representation, inaccuracies in CLASP’s linguistic
analysis can dramatically affect the readability of
its summaries. I discuss ways in which this and
other problems might be overcome.},
year = 1999
}
This file was generated by bibtex2html 1.94.
0 Responses
Stay in touch with the conversation, subscribe to the RSS feed for comments on this post.