Automatic summarization: Difference between revisions

Revision as of 14:19, 24 May 2005

Revision as of 22:23, 3 July 2005

Line 7:

[[Technology|Technologies]] that can make a [[coherent]] summary, of any kind of text, need to take into account several [[variable]]s such as length, writing-style and [[syntax]] to make a useful summary.

One of the major issues of the current automatic summarization research is, how to evaluate the summarization system ? Or, in other words, how to automatically and systematically tell summary A is better than summary B ?

==Extraction and abstraction==

==Extraction and abstractionAbstraction==

Broadly, one distinguishes two approaches: ''[[extraction]]'' and ''[[abstraction]]''.

Extraction techniques merely copy the information deemed most important by the system to the summary, while abstraction involves paraphrasing sections of the [[source document]]. In general, abstraction can condense a text more strongly than extraction, but the programs that can do this are harder to develop.

==Types of summariesSummaries==

== A good example of the use of summarization technology could be search engines such as Google. == A real and online demo

<!--needs to make more clear about how to categorize the type of summaries-->

There are different types of summaries depending what the summarization program focuses on to make the summary of the text, for example ''[[sentence extraction]]generic summaries'', or ''genericquery relevant summaries'' or(sometimes called ''query relevant-biased summaries'').

You can summarize automatically and dynamically a Google hit list by

launching a query via http://www.pertinence.net/google/en

and then clicking "summary" (to the right of "Cached" and "Similar

Pages"). Enter the login "google" and password "google" (you will not have to

type them later).

Pertinence Summarizer's automatic summarization functionality may be

integrated into any other search engine over the Internet or an

Intranet.

It has practical features:

- For all the terms of the query, the corresponding occurrences are

highlighted and you can navigate between occurrences with the Tab key.

- You can summarize the content of the text retrieved by Google, by a

percentage selected from the orange bar (supported formats: MSWord,PDF, txt, html…)

The same function is available for French documents at

http://www.pertinence.net/google/fr

Regards,

A. Lehmam

The Pertinence Mining team

http://www.pertinence.net/index_en.html

--------------------------------------------------------------------------------

==Types of summaries==

There are different types of summaries depending what the summarization program focuses on to make the summary of the text, for example ''[[sentence extraction]] summaries'', ''generic summaries'' or ''query relevant summaries''.

Nowadays, summarization systems are able to create both query relevant text summaries or generic machine-generated summaries depending on what the user needs. Summarization of [[multimedia]] documents, e.g. pictures or movies are also possible.

==Aided summarization==

[[Machine learning]] techniques from closely related fields such as [[Information Retrieval]] or [[Text mining]] have been successfully adapted to help automatic summarization.

Apart from Fully Automated Summarizers (FAS), there are systems that aid users with the task of summarization (MAHS = Machine Aided Human Summarization), for example by highlighting candidate passages to be included in the summary, and there are systems that depend on post-processing by a human (HAMS = Human Aided Machine Summarization).

== Further Reading ==

* Endres-Niggemeyer, Brigitte (1998): Summarizing Information (ISBN 3540637354)

* Mani, Inderjeet (2001): Automatic Summarization (ISBN 1588110605)

==External linkSee Also ==

* [[sentence extraction]]

[http://www.acm.org/sigir/ http://www.acm.org/sigir/]

==External link==

Discover Pertinence Summarizer online :

* [http://www.pertinenceacm.netorg/pssigir/index.jsp?ui.lang=en http://www.pertinenceacm.netorg/pssigir/index.jsp?ui.lang=en]

* [http://www.pertinence.net/google/en Pertinence Summarizer], a commercial webpage summarization demo (lauch a query, click "summary", login: "google", password: "google")