Making fine-grained and coarse-grained sense distinctions, both manually and automatically

被引：41
作者：
Palmer, Martha [1 ]
Dang, Hoa Trang [2 ]
Fellbaum, Christiane [3 ]
机构：
[1] Department of Linguistics, University of Colorado, Boulder, CO
[2] National Institute of Standards and Technology, Gaithersburg, MD
[3] Princeton University, Princeton, NJ
来源：
Natural Language Engineering | 2007年 / 13卷 / 02期
关键词：
D O I：
10.1017/S135132490500402X
中图分类号：
学科分类号：
摘要：
In this paper we discuss a persistent problem arising from polysemy: namely the difficulty of finding consistent criteria for making fine-grained sense distinctions, either manually or automatically. We investigate sources of human annotator disagreements stemming from the tagging for the English Verb Lexical Sample Task in the S ENSEVAL-2 exercise in automatic Word Sense Disambiguation. We also examine errors made by a high-performing maximum entropy Word Sense Disambiguation system we developed. Both sets of errors are at least partially reconciled by a more coarse-grained view of the senses, and we present the groupings we use for quantitative coarse-grained evaluation as well as the process by which they were created. We compare the system's performance with our human annotator performance in light of both fine-grained and coarse-grained sense distinctions and show that well-defined sense groups can be of value in improving word sense disambiguation by both humans and machines. © 2006 Cambridge University Press.
引用
收藏
页码：137 / 163
页数：26
相关论文
共 58 条
  • [1] Asprejan J.D., Regular polysemy, Linguistics, 142, pp. 5-32, (1974)
  • [2] Atkins B.T.S., Levin B., Admitting impediments, Lexical Acquisition: Exploiting On-Line Resources to Build a Lexicon, pp. 233-262, (1991)
  • [3] Berger A.L., Della Pietra S.A., Della Pietra V.J., A maximum entropy approach to natural language processing, Computational Linguistics, 22, 1, (1996)
  • [4] Bikel D.M., Miller S., Schwartz R., Weischedel R., Nymble: A high-performance learning name-finder, Proceedings of the Fifth Conference on Applied Natural Language Processing, (1997)
  • [5] Calzolari N., Corazzari H., Romanseval: Framework and results for italian, Computers and the Humanities, 34, 1-2, (2000)
  • [6] Chodorow M., Leacock C., Miller G.A., A topical/local classifier for word sense identification, Computers and the Humanities, 34, 1-2, (2000)
  • [7] Collins M., Three generative, lexicalised models for statistical parsing, Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics, (1997)
  • [8] Cruse D.A., Lexical Semantics, (1986)
  • [9] Dang H.T., Investigations into the Role of Lexical Semantics in Word Sense Disambiguation, (2004)
  • [10] Dang H.T., Palmer M., Combining contextual features for word sense disambiguation, SIGLEX Workshop on Word Sense Disambiguation, in conjunction with the 40th Meeting of the Association for Computational Linguistics, (ACL-02), (2002)
123456