TPE based tuple extraction method for question and answering system

Jarang Kim, Kyungsoo Kim, Yong Suk Choi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

In order to develop effective question and answering (Q&A) system, it is necessary to analyze syntactic structures of sentence and extract a set of semantically important words (tuple) from them. In this paper, we propose Tree Pattern Expression (TPE) based tuple extraction method for high-performance Q&A system. To extract tuples from target sentences more accurately than conventional Q&A systems, TPE and its fast pattern matching algorithm are used. A tuple consists of subject, predicate, object, preposition and its object, which may contain a correct answer part for a given question. In experiments, our TPE based method performs much better than traditional ones for Q&A system, as we expected, because our method elicits key structures of complicated sentences elaborately and thus extracts their associated tuples more accurately.

Original languageEnglish
Title of host publicationICISA 2014 - 2014 5th International Conference on Information Science and Applications
PublisherIEEE Computer Society
ISBN (Print)9781479944439
DOIs
Publication statusPublished - 2014 Jan 1
Event5th International Conference on Information Science and Applications, ICISA 2014 - Seoul, Korea, Republic of
Duration: 2014 May 62014 May 9

Publication series

NameICISA 2014 - 2014 5th International Conference on Information Science and Applications

Other

Other5th International Conference on Information Science and Applications, ICISA 2014
CountryKorea, Republic of
CitySeoul
Period14/05/614/05/9

    Fingerprint

Keywords

  • Q&A
  • TPE pattern matching algorithm
  • Tree pattern expression(TPE)
  • Tuple extraction

Cite this

Kim, J., Kim, K., & Choi, Y. S. (2014). TPE based tuple extraction method for question and answering system. In ICISA 2014 - 2014 5th International Conference on Information Science and Applications [6847474] (ICISA 2014 - 2014 5th International Conference on Information Science and Applications). IEEE Computer Society. https://doi.org/10.1109/ICISA.2014.6847474