Word Sense Disambiguation: A Survey

被引：932
作者：
Navigli, Roberto [1 ]
机构：
[1] Univ Roma La Sapienza, Dipartimento Informat, I-00198 Rome, Italy
来源：
ACM COMPUTING SURVEYS | 2009年 / 41卷 / 02期
关键词：
Algorithms; Experimentation; Measurement; Performance; Word sense disambiguation; word sense discrimination; WSD; lexical semantics; lexical ambiguity; sense annotation; semantic annotation; CORPUS-BASED METHODS; SPECIAL-ISSUE; KNOWLEDGE SOURCES; WEB; LISTS;
D O I：
10.1145/1459352.1459355
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
Word sense disambiguation (WSD) is the ability to identify the meaning of words in context in a computational manner. WSD is considered an AI-complete problem, that is, a task whose solution is at least as hard as the most difficult problems in artificial intelligence. We introduce the reader to the motivations for solving the ambiguity of words and provide a description of the task. We overview supervised, unsupervised, and knowledge-based approaches. The assessment of WSD systems is discussed in the context of the Senseval/Semeval campaigns, aiming at the objective evaluation of systems participating in several different disambiguation tasks. Finally, applications, open problems, and future directions are discussed.
引用
收藏
页数：69
相关论文
共 279 条
[1]  
Abney S, 2004, COMPUT LINGUIST, V30, P364
[2]  
Abney S., 1999, Proceedings of the ACL Workshop on Unsupervised Learning in Natural Language Processing, P1
[3]  
Agirre E, 2006, TEXT SPEECH LANG TEC, V33, P1, DOI 10.1007/978-1-4020-4809-8
[4]  
AGIRRE E, 2007, P 4 INT WORKSH SEM E, P1
[5]  
AGIRRE E, 1996, P 16 INT C COMP LING, P16
[6]  
AGIRRE E, 2007, P 4 INT WORKSH SEM E, P342
[7]  
AGIRRE E, 2000, P COLING 2000 WORKSH, P11
[8]  
AGIRRE E, 2001, P NAACL WORKSH WORDN, P23
[9]  
AGIRRE E, 2003, P C REC ADV NAT LANG, P121
[10]  
Agirre E., 2007, P 4 INT WORKSH SEM E
12345678910