Automatic summarization: Difference between revisions

Revision as of 19:41, 24 September 2004

Revision as of 20:05, 24 September 2004

Line 2:

{{cleanup}}

'''Automatic Summarization''' is the automated creation of a summary[[short]]ened version of anya kind[[text]] ofby a [[textcomputer program]]. Ideally,The theproduct systemof shouldthis beprocedure sensitivestill tocontains the usersmost needsimportant points of the original text.

Access to [[coherent]] and correctly-developed text summaries can be of great use, especially in our time of [[information overload]], in which the amount of information electronically available growsto dayus, grows byevery day. A good example of the use of summarization technology could be [[search engine]]s such as [[Google]].

[[technology | technologies]] that can make a [[coherent]] summary, of any kind of text, taking into account varying content such as length, writing-style, [[syntax]], etc. have to solve a variety of problems.

[[technology Technology| technologiesTechnologies]] that can make a [[coherent]] summary, of any kind of text, takingneed to take into account varyingseveral content[[variable]]s such as length, writing-style, and [[syntax]], etc. have to solvemake a varietyuseful of problemssummary.

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.

==Extraction and abstraction==

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

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

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.

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 program.

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

==Types of summaries==

Apart from fully automated summarizers (FAS) there are systems that aid humans 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 translation).

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

Access to coherent and correctly-developed text summaries can be of great use, especially in our time of [[information overload]], in which the amount of information electronically available grows day by day. A good example of the summarization technology could be [[search engine]]s such as [[Google]].

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

Apart from fullyFully automatedAutomated summarizersSummarizers (FAS), there are systems that aid humansusers with the task of summarization (MAHS = machineMachine aidedAided humanHuman summarizationSummarization), 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 = humanHuman aidedAided machineMachine translationSummarization).

== Further Reading ==

==Overviews==

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

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

==PapersExternal link==

==See also==

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