Automatic Summarization Online

The program for the NAACL Workshop on Evaluation Metrics and System Comparison for Automatic Summarization

admin — Mon, 14 May 2012 17:00:17 +0000

The program for the NAACL Workshop on Evaluation Metrics and System Comparison for Automatic Summarization was published. One of the slots is dedicated to a new pilot task on Summarization of scientific literature. Hopefully both the papers and more details about the task will become available. This workshop is another proof of the revival of the automatic summarisation field.

New summarisation competition

admin — Mon, 26 Mar 2012 16:36:08 +0000

The Tweet Contextualization competition organised at CLEF 2012 in Rome asks participants to produce a text on the basis of a tweet which provides some context about the subject of the tweet, in order to help a reader understand it. Essentially this is a multi-document summary produced from Wikipedia articles. The output should be a readable summary, not exceeding 500 words.

For more information visit https://inex.mmci.uni-saarland.de/tracks/qa/.

Tutorial on how to run ROUGE

admin — Fri, 16 Mar 2012 15:54:15 +0000

These days, ROUGE is the most commonly used metric for evaluating summaries. This is also due to the fact that it is possible to download a program that calculates the ROUGE score for you. Unfortunately, at times it can be difficult to configure and run the script. A tutorial on how you can setup the script can be found at http://kavita-ganesan.com/rouge-howto. In addition, in the same blog you can find a perl script that prepares your data to be evaluated using ROUGE and another script that helps you interpret the result.

What is data mining?

admin — Mon, 07 Jun 2010 15:24:03 +0000

Marginally relevant to automatic summarisation, but quite a nice introduction by Prof. Stephan P Kudyba from NJIT School of Managemen to what data mining is and how it is being used in the business world. Not as funny as the beer & diapers classic example used in data mining, but more authentic.

New corpus for automatic summarisation

admin — Tue, 23 Feb 2010 23:28:49 +0000

It is nice to see that people still create resources for automatic summarisation. A few days ago, The Essex Arabic Summaries Corpus (EASC) was announced on corpora list. The corpus contains 153 Arabic articles and 765 human-generated extractive summaries produced using Mechanical Turk. The authors state that the corpus contains copyrighted material and it is the responsibility of the users to makes sure they comply with the legislation in their country. Unfortunately no further information is given in order to know what material was used. The annotation is freely available for research purposes and is distributed under the Creative Commons Attributive/Share Alike license. As a bonus the corpus comes with an Arabic version of ROUGE.

The corpus cannot be downloaded directly. Instead the author needs to be contacted.

Tutorial on automatic summarisation at RANLP2009

admin — Tue, 15 Sep 2009 07:21:24 +0000

A new tutorial on automatic summarisation from RANLP2009 was added to the site. It can be viewed online using iPaper or downloaded for offline reading.

Tutorial on automatic summarization

View more presentations from Constantin Orasan

Hello world!

admin — Tue, 01 Sep 2009 08:04:51 +0000

Welcome the the Automatic Summarization Online web site. The purpose of this web site is to provide pointers and information relevant to the field of automatic summarisation. For the moment there is not that much, but hopefully more information will be added in the coming weeks and months.