nips nips2004 nips2004-101 nips2004-101-reference knowledge-graph by maker-knowledge-mining

101 nips-2004-Learning Syntactic Patterns for Automatic Hypernym Discovery


Source: pdf

Author: Rion Snow, Daniel Jurafsky, Andrew Y. Ng

Abstract: Semantic taxonomies such as WordNet provide a rich source of knowledge for natural language processing applications, but are expensive to build, maintain, and extend. Motivated by the problem of automatically constructing and extending such taxonomies, in this paper we present a new algorithm for automatically learning hypernym (is-a) relations from text. Our method generalizes earlier work that had relied on using small numbers of hand-crafted regular expression patterns to identify hypernym pairs. Using “dependency path” features extracted from parse trees, we introduce a general-purpose formalization and generalization of these patterns. Given a training set of text containing known hypernym pairs, our algorithm automatically extracts useful dependency paths and applies them to new corpora to identify novel pairs. On our evaluation task (determining whether two nouns in a news article participate in a hypernym relationship), our automatically extracted database of hypernyms attains both higher precision and higher recall than WordNet. 1


reference text

[1] Caraballo, S.A. (2001) Automatic Acquisition of a Hypernym-Labeled Noun Hierarchy from Text. Brown University Ph.D. Thesis.

[2] Cederberg, S. & Widdows, D. (2003) Using LSA and Noun Coordination Information to Improve the Precision and Recall of Automatic Hyponymy Extraction. Proc. of CoNLL-2003, pp. 111–118.

[3] Ciaramita, M. & Johnson, M. (2003) Supersense Tagging of Unknown Nouns in WordNet. Proc. of EMNLP-2003.

[4] Ciaramita, M., Hofmann, T., & Johnson, M. (2003) Hierarchical Semantic Classification: Word Sense Disambiguation with World Knowledge. Proc. of IJCAI-2003.

[5] Fellbaum, C. (1998) WordNet: An Electronic Lexical Database. Cambridge, MA: MIT Press.

[6] Girju, R., Badulescu A., & Moldovan D. (2003) Learning Semantic Constraints for the Automatic Discovery of Part-Whole Relations. Proc. of HLT-2003.

[7] Harman, D. (1992) The DARPA TIPSTER project. ACM SIGIR Forum 26(2), Fall, pp. 26–28.

[8] Hearst, M. (1992) Automatic Acquisition of Hyponyms from Large Text Corpora. Proc. of the Fourteenth International Conference on Computational Linguistics, Nantes, France.

[9] Hearst, M. & Sch¨ tze, H. (1993) Customizing a lexicon to better suit a computational task. In u Proc. of the ACL SIGLEX Workshop on Acquisition of Lexical Knowledge from Text.

[10] Lin, D. (1998) Dependency-based Evaluation of MINIPAR. Workshop on the Evaluation of Parsing Systems, Granada, Spain

[11] Lin, D. & Pantel P. (2001) Discovery of Inference Rules for Question Answering. Natural Language Engineering, 7(4), pp. 343–360.

[12] Pantel, P. (2003) Clustering by Committee. Ph.D. Dissertation. Department of Computing Science, University of Alberta.

[13] Pantel, P. & Ravichandran, D. (2004) Automatically Labeling Semantic Classes. Proc. of NAACL-2004.

[14] Pereira, F., Tishby, N., & Lee, L. (1993) Distributional Clustering of English Words. Proc. of ACL-1993, pp. 183–190.

[15] Ravichandran, D. & Hovy, E. (2002) Learning Surface Text Patterns for a Question Answering system. Proc. of ACL-2002.

[16] Rennie J., Shih, L., Teevan, J., & Karger, D. (2003) Tackling the Poor Assumptions of Naive Bayes Text Classifiers. Proc. of ICLM-2003.

[17] Riloff, E. & Shepherd, J. (1997) A Corpus-Based Approach for Building Semantic Lexicons. Proc of EMNLP-1997.

[18] Roark, B. & Charniak, E. (1998) Noun-phrase co-occurerence statistics for semi-automaticsemantic lexicon construction. Proc. of ACL-1998, 1110–1116.

[19] Tseng, H. (2003) Semantic classification of unknown words in Chinese. Proc. of ACL-2003.

[20] Turney, P.D., Littman, M.L., Bigham, J. & Shanyder, V. (2003) Combining independent modules to solve multiple-choice synonym and analogy problems. Proc. of RANLP-2003, pp. 482–489.

[21] Widdows, D. (2003) Unsupervised methods for developing taxonomies by combining syntactic and statistical information. Proc. of HLT/NAACL 2003, pp. 276–283.