emnlp emnlp2012 emnlp2012-76 emnlp2012-76-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Lev Ratinov ; Dan Roth
Abstract: We explore the interplay of knowledge and structure in co-reference resolution. To inject knowledge, we use a state-of-the-art system which cross-links (or “grounds”) expressions in free text to Wikipedia. We explore ways of using the resulting grounding to boost the performance of a state-of-the-art co-reference resolution system. To maximize the utility of the injected knowledge, we deploy a learningbased multi-sieve approach and develop novel entity-based features. Our end system outperforms the state-of-the-art baseline by 2 B3 F1 points on non-transcript portion of the ACE 2004 dataset.
A. Bagga and B. Baldwin. 1998. Algorithms for scoring coreference chains. In MUC7. E. Bengtson and D. Roth. 2008. Understanding the value of features for coreference resolution. In EMNLP. 14YAGO uses WordNet to expand its set of facts. For example, if Martha Stewart is assigned the meaning personality from category head words analysis, YAGO adds the meaning celebrity because personality is a direct hyponym of celebrity in WordNet. However, this is done offline in a context-insensitive way, which is inherently limited. R. C. Bunescu and M. Pasca. 2006. Using encyclopedic knowledge for named entity disambiguation. In EACL. S. Cucerzan. 2007. Large-scale named entity disambiguation based on Wikipedia data. In EMNLPCoNLL. A. Culotta, M. Wick, R. Hall, and A. McCallum. 2007. First-order probabilistic models for coreference resolution. In HLT/NAACL, pages 81–88. Q. Do, D. Roth, M. Sammons, Y. Tu, and V. Vydiswaran. 2009. Robust, light-weight approaches to compute lexical similarity. Technical report, University of Illinois at Urbana-Champaign. A. Fader, S. Soderland, and O. Etzioni. 2009. Scaling wikipedia-based named entity disambiguation to arbitrary web text. In WikiAI (IJCAI workshop). Y. Goldberg and M. Elhadad. 2010. An efficient algorithm for easy-first non-directional dependency parsing. In NAACL. A. Haghighi and D. Klein. 2009. Simple coreference resolution with rich syntactic and semantic features. In EMNLP. A. Haghighi and D. Klein. 2010. Coreference resolution in a modular, entity-centered model. In HLT-ACL. Association for Computational Linguistics. T. Joachims, T. Hofmann, Y. Yue, and C. Yu. 2009. Predicting structured objects with support vector machines. Communications of the ACM, Research Highlight, 52(1 1):97–104, November. X. Luo. 2005. On coreference resolution performance metrics. In HLT. R. Mihalcea and A. Csomai. 2007. Wikify! : linking documents to encyclopedic knowledge. In CIKM. D. Milne and I. H. Witten. 2008. Learning to link with wikipedia. In CIKM. V. Nastase and M. Strube. 2008. Decoding wikipedia categories for knowledge acquisition. In AAAI. V. Ng and C. Cardie. 2002. Improving machine learning approaches to coreference resolution. In ACL. NIST. 2004. The ace evaluation plan. www.nist.gov/speech/tests/ace/index.htm. S. P. Ponzetto and M. Strube. 2006. Exploiting semantic role labeling, wordnet and wikipedia for coreference resolution. In HLT-ACL. K. Raghunathan, H. Lee, S. Rangarajan, N. Chambers, M. Surdeanu, D. Jurafsky, and C. Manning. 2010. A multi-pass sieve for coreference resolution. In EMNLP. A. Rahman and V. Ng. 2011. Coreference resolution with world knowledge. In HLT-ACL. L. Ratinov, D. Downey, M. Anderson, and D. Roth. 2011. Local and global algorithms for disambiguation to wikipedia. In ACL. 1244 M. Strube and S. P. Ponzetto. 2006. WikiRelate! Computing Semantic Relatedness Using Wikipedia. In Proceedings of the Twenty-First National Conference on Artificial Intelligence, July. F. M. Suchanek, G. Kasneci, and G. Weikum. 2007. Yago: A core of semantic knowledge. In WWW. D. Vadas and J. R. Curran. 2008. Parsing noun phrase structure with CCG. In ACL. M. Vilain, J. Burger, J. Aberdeen, D. Connolly, and L. Hirschman. 1995. A model-theoretic coreference scoring scheme. In MUC6, pages 45–52. R. Vilalta and I. Rish. 2003. A decomposition of classes via clustering to explain and improve naive bayes. In ECML. M. Wick, K. Rohanimanesh, K. Bellare, A. Culotta, and A. McCallum. 2011. Samplerank: Training factor graphs with atomic gradients. In ICML.