Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Resource Lean and Portable Automatic Text Summarization
KTH, School of Computer Science and Communication (CSC), Numerical Analysis and Computer Science, NADA.
2007 (English)Doctoral thesis, comprehensive summary (Other scientific)
Abstract [en]

Today, with digitally stored information available in abundance, even for many minor languages, this information must by some means be filtered and extracted in order to avoid drowning in it. Automatic summarization is one such technique, where a computer summarizes a longer text to a shorter non-rendundant form. Apart from the major languages of the world there are a lot of languages for which large bodies of data aimed at language technology research to a high degree are lacking. There might also not be resources available to develop such bodies of data, since it is usually time consuming and requires substantial manual labor, hence being expensive. Nevertheless, there will still be a need for automatic text summarization for these languages in order to subdue this constantly increasing amount of electronically produced text.

This thesis thus sets the focus on automatic summarization of text and the evaluation of summaries using as few human resources as possible. The resources that are used should to as high extent as possible be already existing, not specifically aimed at summarization or evaluation of summaries and, preferably, created as part of natural literary processes. Moreover, the summarization systems should be able to be easily assembled using only a small set of basic language processing tools, again, not specifically aimed at summarization/evaluation. The summarization system should thus be near language independent as to be quickly ported between different natural languages.

The research put forth in this thesis mainly concerns three computerized systems, one for near language independent summarization – The HolSum summarizer; one for the collection of large-scale corpora – The KTH News Corpus; and one for summarization evaluation – The KTH eXtract Corpus. These three systems represent three different aspects of transferring the proposed summarization method to a new language.

One aspect is the actual summarization method and how it relates to the highly irregular nature of human language and to the difference in traits among language groups. This aspect is discussed in detail in Chapter 3. This chapter also presents the notion of “holistic summarization”, an approach to self-evaluative summarization that weighs the fitness of the summary as a whole, by semantically comparing it to the text being summarized, before presenting it to the user. This approach is embodied as the text summarizer HolSum, which is presented in this chapter and evaluated in Paper 5.

A second aspect is the collection of large-scale corpora for languages where few or none such exist. This type of corpora is on the one hand needed for building the language model used by HolSum when comparing summaries on semantic grounds, on the other hand a large enough set of (written) language use is needed to guarantee the randomly selected subcorpus used for evaluation to be representative. This topic briefly touched upon in Chapter 4, and detailed in Paper 1.

The third aspect is, of course, the evaluation of the proposed summarization method on a new language. This aspect is investigated in Chapter 4. Evaluations of HolSum have been run on English as well as on Swedish, using both well established data and evaluation schemes (English) as well as with corpora gathered “in the wild” (Swedish). During the development of the latter corpora, which is discussed in Paper 4, evaluations of a traditional sentence ranking text summarizer, SweSum, have also been run. These can be found in Paper 2 and 3.

This thesis thus contributes a novel approach to highly portable automatic text summarization, coupled with methods for building the needed corpora, both for training and evaluation on the new language.

Abstract [sv]

Idag, med ett överflöd av digitalt lagrad information även för många mindre språk, är det nära nog omöjligt att manuellt sålla och välja ut vilken information man ska ta till sig. Denna information måste istället filteras och extraheras för att man inte ska drunkna i den. En teknik för detta är automatisk textsammanfattning, där en dator sammanfattar en längre text till en kortare icke-redundant form. Vid sidan av de stora världsspråken finns det många små språk för vilka det saknas stora datamängder ämnade för språkteknologisk forskning. För dessa saknas det också ofta resurser för att bygga upp sådana datamängder då detta är tidskrävande och ofta dessutom kräver en ansenlig mängd manuellt arbete. Likväl behövs automatisk textsammanfattning för dessa språk för att tämja denna konstant ökande mängd elektronsikt producerad text.

Denna avhandling sätter således fokus på automatisk sammanfattning av text med så liten mänsklig insats som möjligt. De använda resurserna bör i så hög grad som möjligt redan existera, inte behöva vara skapade för automatisk textsammanfattning och helst även ha kommit till som en naturlig del av en litterär process. Vidare, sammanfattningssystemet bör utan större ansträngning kunna sättas samman med hjälp av ett mindre antal mycket grundläggande språkteknologiska verktyg, vilka inte heller de är specifikt ämnade för textsammanfattning. Textsammanfattaren bör således vara nära nog språkoberoende för att det med enkelhet kunna att flyttas mellan ett språk och ett annat.

Den forskning som läggs fram i denna avhandling berör i huvudsak tre datorsystem, ett för nära nog språkoberoende sammanfattning – HolSum; ett för insamlande av stora textmängder – KTH News Corpus; och ett för utvärdering av sammanfattning – KTH eXtract Corpus. Dessa tre system representerar tre olika aspekter av att föra över den framlagda sammanfattningsmetoden till ett nytt språk.

En aspekt är den faktiska sammanfattningsmetoden och hur den påverkas av mänskliga språks högst oregelbundna natur och de skillnader som uppvisas mellan olika språkgrupper. Denna aspekt diskuteras i detalj i kapitel tre. I detta kapitel presenteras också begreppet “holistisk sammanfattning”, en ansats tillsjälvutvärderande sammanfattning vilken gör en innehållslig bedömning av sammanfattningen som en helhet innan den presenteras för användaren. Denna ansats förkroppsligas i textsammanfattaren HolSum, som presenteras i detta kapitel samt utvärderas i artikel fem.

En andra aspekt är insamlandet av stora textmängder för språk där sådana saknas. Denna typ av datamängder behövs dels för att bygga den språkmodell som HolSum använder sig av när den gör innehållsliga jämförelser sammanfattningar emellan, dels behövs dessa för att ha en tillräckligt stor mängd text att kunna slumpmässigt extrahera en representativ delmängd lämpad för utvärdering ur. Denna aspekt berörs kortfattat i kapitel fyra och i mer önskvärd detalj i artikel ett.

Den tredje aspekten är, naturligtvis, utvärdering av den framlagda sammanfattningsmetoden på ett nytt språk. Denna aspekt ges en översikt i kapitel 4. Utvärderingar av HolSum har utförts både med väl etablerade datamängder och utvärderingsmetoder (för engelska) och med data- och utvärderingsmängder insamlade specifikt för detta ändamål (för svenska). Under sammanställningen av denna senare svenska datamängd, vilken beskrivs i artikel fyra, så utfördes även utvärderingar av en traditionell meningsextraherande textsammanfattare, SweSum. Dessa återfinns beskrivna i artikel två och tre.

Denna avhandling bidrar således med ett nydanande angreppssätt för nära nog språkoberoende textsammanfattning, uppbackad av metoder för sammansättning av erforderliga datamängder för såväl modellering av som utvärdering på ett nytt språk.

Place, publisher, year, edition, pages
Stockholm: KTH , 2007. , vii, 132 p.
Series
Trita-CSC-A, ISSN 1653-5723 ; 2007:9
Keyword [en]
holsum, language independent, holistic, summarization, lexical semantics, co-occurrence statistics, word space model, bag-of-words, bag-of-concepts, random indexing, swesum, news corpus, extract corpus
National Category
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-4414ISBN: 978-91-7178-704-0 (print)OAI: oai:DiVA.org:kth-4414DiVA: diva2:12198
Public defence
2007-06-11, E2, Huvudbyggnaden, Lindstedtsvägen 3, Stockholm, 13:15
Opponent
Supervisors
Note
QC 20100712Available from: 2007-05-31 Created: 2007-05-31 Last updated: 2010-07-12Bibliographically approved
List of papers
1. Internet as Corpus: Automatic Construction of a Swedish News Corpus
Open this publication in new window or tab >>Internet as Corpus: Automatic Construction of a Swedish News Corpus
2001 (English)Report (Other academic)
Abstract [en]

This paper describes the automatic building of a corpus of short Swedish news texts from the Internet, itsapplication and possible future use. The corpus is aimed at research on Information Retrieval, InformationExtraction, Named Entity Recognition and Multi Text Summarization. The corpus has been constructed by usingan Internet agent, the so called newsAgent, downloading Swedish news text from various sources. A small partof this corpus has then been manually tagged with keywords and named entities. The newsAgent is also used asa workbench for processing the abundant flows of news texts for various users in a customized format in theapplication Nyhetsguiden.

Place, publisher, year, edition, pages
Stockholm: KTH, 2001. 5 p.
Series
Trita-NA-P, 0117
Series
IPLab, 195
Keyword
News text, Corpus, Swedish, Internet
National Category
Computer Science
Identifiers
urn:nbn:se:kth:diva-14075 (URN)
Note
QC 20100712. Även publicerad i "Proceedings of NODALIDA’01 – 13th Nordic Conference on Computational Linguistics, Uppsala, Sweden, May 21–22 2001."Available from: 2010-07-12 Created: 2010-07-12 Last updated: 2010-07-16Bibliographically approved
2. Development of a Swedish Corpus for Evaluating Summarizers and other IR-tools
Open this publication in new window or tab >>Development of a Swedish Corpus for Evaluating Summarizers and other IR-tools
2001 (English)Report (Other academic)
Abstract [en]

We are presenting the construction of a Swedish corpus aimed at research1on Information Retrieval, Information Extraction, Named Entity Recognitionand Multi Text Summarization, we will also present the results on evaluatingour Swedish text summarizer SweSum with this corpus. The corpus has beenconstructed by using Internet agents downloading Swedish newspaper textfrom various sources. A small part of this corpus has then been manuallyannotated. To evaluate our text summarizer SweSum we let ten studentsexecute our text summarizer with increasing compression rates on the 100manually annotated texts to find answers to predefined questions. The resultsshowed that at 40 percent summarization/compression rate the correct answerrate was 84 percent.

Place, publisher, year, edition, pages
Stockholm: KTH, 2001. 7 p.
National Category
Computer Science
Identifiers
urn:nbn:se:kth:diva-14077 (URN)
Note
QC 20100712Available from: 2010-07-12 Created: 2010-07-12 Last updated: 2010-07-16Bibliographically approved
3. Exploitation of Named Entities in Automatic Text Summarization for Swedish
Open this publication in new window or tab >>Exploitation of Named Entities in Automatic Text Summarization for Swedish
2003 (English)In: Proceedings of NODALIDA’03 – 14th Nordic Conferenceon Computational Linguistics, Reykjavik, Iceland, May 30–31 2003gs of ., 2003, 9- p.Conference paper, Published paper (Other academic)
Abstract [en]

Named Entities are often seen as important cues to the topic of a text. Theyare among the most information dense tokens of the text and largely definethe domain of the text. Therefore, Named Entity Recognition should greatlyenhance the identification of important text segments when used by an (extractionbased) automatic text summarizer. We have compared Gold Standardsummaries produced by majority votes over a number of manually createdextracts with extracts created with our extraction based summarization system,SweSum. Furthermore we have taken an in-depth look at how overweightingof named entities affects the resulting summary and come to theconclusion that weighting of named entities should be carefully consideredwhen used in a naïve fashion.

National Category
Computer Science
Identifiers
urn:nbn:se:kth:diva-14081 (URN)
Conference
NODALIDA’03 – 14th Nordic Conferenceon Computational Linguistics, Reykjavik, Iceland, May 30–31 2003
Note
QC 20100712Available from: 2010-07-12 Created: 2010-07-12 Last updated: 2010-07-16Bibliographically approved
4. Generation of Reference Summaries
Open this publication in new window or tab >>Generation of Reference Summaries
2005 (English)In: Proceedings of 2nd Language & Technology Conference: Human LanguageTechnologies as a Challenge for Computer Science and Linguistics, Poznan, Poland,April 21–23 2005., 2005, 6- p.Conference paper, Published paper (Other academic)
Abstract [en]

We have constructed an integrated web-based system for collection of extract-based corpora and for evaluation of summaries andsummarization systems. During evaluation and examination of the collected and generated data we found that in a situation of lowagreement among the informants the corpus gives unduly favors to summarization systems that use sentence position as a centralweighting feature. The problem is discussed and a possible solution is outlined.

National Category
Computer Science
Identifiers
urn:nbn:se:kth:diva-14085 (URN)
Conference
2nd Language & Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics, Poznan, Poland, April 21–23 2005.
Note
QC 20100712Available from: 2010-07-12 Created: 2010-07-12 Last updated: 2010-09-22Bibliographically approved
5. Navigating Through Summary Space: Selecting Summaries, Not Sentences
Open this publication in new window or tab >>Navigating Through Summary Space: Selecting Summaries, Not Sentences
(English)Manuscript (preprint) (Other academic)
Abstract [en]

We present a novel method for extraction based summarization using statisticallexical semantics. It attempts to give an overview by selecting thesummary most similar to the source text from a set of possible candidates.It evaluates whole summaries at once, making no judgments on for instanceindividual sentences. A simple greedy search strategy can be used to searchthrough a space of possible summaries. Starting the search with the leadingsentences of the source text is a powerful heuristic, but we also evaluateother search strategies. The aim has been to construct a summarizer thatcan be quickly assembled, with the use of only a very few basic languagetools. The proposed method is largely language independent and can beused even for languages that lack large amounts of structured or annotateddata, or advanced tools for linguistic processing. When evaluated on Englishabstracts from the Document Understanding Conferences it performs well,though better language specific systems are available. It performs betterthan several of the systems evaluated there, but worse than the best systems.We have also evaluated our method on a corpus of human made extractsin Swedish. It performed poorly compared to a traditional extraction-basedsummarizer. However, since these man-made extracts were not produced toreflect the whole contents of the texts, but rather to cover only the main topic,this was expected.

National Category
Computer Science
Identifiers
urn:nbn:se:kth:diva-14086 (URN)
Note
QC 20100712Available from: 2010-07-12 Created: 2010-07-12 Last updated: 2010-07-12Bibliographically approved

Open Access in DiVA

fulltext(1828 kB)843 downloads
File information
File name FULLTEXT01.pdfFile size 1828 kBChecksum MD5
5efe470317106018904dca043d9047579ff85fe39050052dab9d7982f118c96852303a9f
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Hassel, Martin
By organisation
Numerical Analysis and Computer Science, NADA
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 843 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 2118 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf