Accurate semantic class classifier for coreference resolution
|Accurate semantic class classifier for coreference resolution|
|Author(s)||Huang Z., Zeng G., Xu W., Celikyilmaz A.|
|Published in||EMNLP 2009 - Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: A Meeting of SIGDAT, a Special Interest Group of ACL, Held in Conjunction with ACL-IJCNLP 2009|
|Keyword(s)||Unknown (Extra: Anaphors, Baseline systems, Classification errors, Coreference, Coreference resolution, Knowledge sources, Named entities, Semantic class, Semantic knowledge, Wikipedia, Wordnet, Computational linguistics, Ontology, Semantics, Natural language processing systems)|
|Article||BASE, CiteSeerX, Google Scholar|
|Web||Ask, Bing, Google (PDF), Yahoo!|
|Download and mirrors|
|Local copy||Not available|
|Remote mirror(s)||Not available|
|Export and share|
|BibTeX, CSV, RDF, JSON|
|Browse properties · List of conference papers|
Accurate semantic class classifier for coreference resolution is a 2009 conference paper written in English by Huang Z., Zeng G., Xu W., Celikyilmaz A. and published in EMNLP 2009 - Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: A Meeting of SIGDAT, a Special Interest Group of ACL, Held in Conjunction with ACL-IJCNLP 2009.
There have been considerable attempts to incorporate semantic knowledge into coreference resolution systems: different knowledge sources such as WordNet and Wikipedia have been used to boost the performance. In this paper, we propose new ways to extract WordNet feature. This feature, along with other features such as named entity feature, can be used to build an accurate semantic class (SC) classifier. In addition, we analyze the SC classification errors and propose to use relaxed SC agreement features. The proposed accurate SC classifier and the relaxation of SC agreement features on ACE2 coreference evaluation can boost our baseline system by 10.4% and 9.7% using MUC score and anaphor accuracy respectively.
- This section requires expansion. Please, help!
Probably, this publication is cited by others, but there are no articles available for them in WikiPapers. Cited 3 time(s)