Advertisement

Are Human-Input Seeds Good Enough for Entity Set Expansion? Seeds Rewriting by Leveraging Wikipedia Semantic Knowledge

  • Zhenyu Qi
  • Kang Liu
  • Jun Zhao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7675)

Abstract

Entity Set Expansion is an important task for open information extraction, which refers to expanding a given partial seed set to a more complete set that belongs to the same semantic class. Many previous researches have proved that the quality of seeds can influence expansion performance a lot since human-input seeds may be ambiguous, sparse etc. In this paper, we propose a novel method which can generate new, high-quality seeds and replace original, poor-quality ones. In our method, we leverage Wikipedia as a semantic knowledge to measure semantic relatedness and ambiguity of each seed. Moreover, to avoid the sparseness of the seed, we use web resources to measure its population. Then new seeds are generated to replace original, poor-quality seeds. Experimental results show that new seed sets generated by our method can improve entity expansion performance by up to average 9.1% over original seed sets.

Keywords

information extraction seed rewrite semantic knowledge 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Richard, W., Nico, S., William, C., Eric, N.: Automatic Set Expansion for List Question Answering. In: Proceedings of EMNLP 2008, pp. 947–954. ACL, USA (2008)Google Scholar
  2. 2.
    Vishnu, V., Patrick, P., Eric, C.: Helping editors choose better seed sets for entity set. In: Proceedings of CIKM 2009, pp. 225–234. ACM, Hong Kong (2009)Google Scholar
  3. 3.
    Marco, P., Patrick, P.: Entity Extraction via Ensemble Semantics. In: Proceedings of EMNLP 2009, pp. 238–247. ACL, Singapore (2009)Google Scholar
  4. 4.
    Luis, S., Valentiin, J.: More Like These: Growing Entity Classes from Seeds. In: Proceedings of CIKM 2007, pp. 959–962. ACM, Portugal (2007)Google Scholar
  5. 5.
    Richard, W., William, C.: Automatic Set Instance Extraction using the Web. In: Proceedings of ACL/AFNLP 2009, pp. 441–449. ACL, Singapore (2009)Google Scholar
  6. 6.
    Patrick, P., Eric, C., Arkady, B., Ana-Maria, P., Vishnu, V.: Web-Scale Distributional Similarity and Entity Set Expansion. In: Proceedings of EMNLP 2009, Singapore, pp. 938–947 (2009)Google Scholar
  7. 7.
    Yeye, H., Dong, X.: SEISA Set Expansion by Iterative Similarity Aggregation. In: Proceedings of WWW 2011, pp. 427–436. ACM, India (2011)Google Scholar
  8. 8.
    Marius, P.: Weakly-supervised discovery of named entities using web search queries. In: Proceedings of CIKM 2007, pp. 683–690. ACM, Portugal (2007)Google Scholar
  9. 9.
    Richard, W., William, C.: Iterative set expansion of named entities using the web. In: Proceedings of ICDM 2008, pp. 1091–1096. IEEE Computer Society, Italy (2008)Google Scholar
  10. 10.
    Richard, W., William, C.: Language-Independent Set Expansion of Named Entities using the Web. In: Proceedings of ICDM 2007, USA, pp. 342–350. IEEE Computer Society (2007)Google Scholar
  11. 11.
    David, M., Ian, H.W.: Learning to link with Wikipedia. In: Proceedings of CIKM 2008, pp. 509–518. ACM, USA (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Zhenyu Qi
    • 1
  • Kang Liu
    • 1
  • Jun Zhao
    • 1
  1. 1.National Laboratory of Pattern Recognition(NLPR)Institute of Automation Chinese Academy of SciencesBeijingChina

Personalised recommendations