NDLI: Acquiring Paraphrases from Corpora and Its Application to Machine Translation

Please wait, while we are loading the content...

Acquiring Paraphrases from Corpora and Its Application to Machine Translation

Content Provider	Semantic Scholar
Author	Shimohata, Mitsuo
Copyright Year	2004
Abstract	A natural language contains various paraphrases, that is, superficially different expressions that share the same meaning. Such a wide variety of paraphrases reflects the rich expressiveness of natural language, while causing difficulty in natural language processing applications, such as machine translation (MT). For MT, this variety reduces the coverage of translatable input sentences and complicates language too much to comprehend every possible variation. Unfortunately, existing resources for paraphrases do not adequately deal with the difficulty because their paraphrase knowledge only covers general areas and has little effect on uses for specific domains and applications. This thesis describes corpus-based paraphrase acquisition and its application to MT. We propose two paraphrase acquisition methods: lexical paraphrases and sentential paraphrases, each of which has its own advantages. Both methods are based on shallow analysis, and rely on a corpus but no other resource. The achievements described in this thesis consist of three parts: analysis of manual paraphrases, automatic acquisition of lexical paraphrases, and similar sentence retrieval, which corresponds to sentential paraphrasing. First, we describe two analyses of human paraphrases to clarify the following questions: (1) what types of paraphrases are dominant? and (2) how can human paraphrases be effective for MT? These investigations suggest that lexical paraphrasing and sentential paraphrasing are dominant in travel conversation domains. Second, we describe a method for extracting lexical paraphrases from a parallel corpus. This method has two advantages: (1) it acquires not only synonymous content ∗Doctoral Dissertation, Department of Information Processing, Graduate School of Information Science, Nara Institute of Science and Technology, NAIST-IS-DD0261014, September 15, 2004.
File Format	PDF HTM / HTML
Alternate Webpage(s)	http://cl.aist-nara.ac.jp/thesis/dthesis-shimohata.pdf
Language	English
Access Restriction	Open
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in