Yarowsky, David. 1995. Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of the 33rd annual meeting of the Association of Computational Linguistics, pages 189--196. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
First 50 documents Next 50
A Probabilistic Approach to Lexical Semantic Knowledge Acquisition.. - Li (1998) (Correct)
.... 1996) For word sense disambiguation methods, see also (Black, 1988; Brown et al. 1991; Guthrie et al. 1991; Gale, Church, and Yarowsky, 1992; McRoy, 1992; Leacock, Towell, and Voorhees, 1993; Yarowsky, 1993; Bruce and Wiebe, 1994; Niwa and Nitta, 1994; Voorhees, Leacock, and Towell, 1995; Yarowsky, 1995; Golding and Schabes, 1996; Ng and Lee, 1996; Fujii et al. 1996; Schutze, 1997; Schutze, 1998) A probabilistic decision list (Yamanishi, 1992a) is a kind of conditional distribution and di#erent from a deterministic decision list (Rivest, 1987) which is a kind of Boolean function. Winnow ....
Yarowsky, David. 1995. Unsupervised word sense disambiguation rivaling supervised methods. Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics, pages 189--196. Appendix A A.1 Derivation of Description Length: Two-stage
Unsupervised Learning of Name Structure from Coreference Data - Charniak (Correct)
....was then used to suggest the gender of the noun phrase that was proposed as the antecedent. The current work is quite di#erent in both goal and methods, but similar in spirit. More generally this work is part of a growing body of work on learning language related information from unlabeled corpora [1,2,3,8,9,10, 11]. 2 Problem Definition and Data Preparation We assume that people s names have six (optional) components as exemplified in the following somewhat contrived example: Word Label Label Number Defense descriptor 0 Secretary descriptor 0 Mr. honorific 1 John first name 2 W. middle name 3 ....
Yarowsky, D. Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics. 1995, 189--196.
Semantic Knowledge Construction From Annotated Image Collections - Benitez, Chang (2002) (5 citations) (Correct)
....describing their content (e.g. caption or web page of an image, respectively) both text and images can be used and integrated into the semantic knowledge extraction process. Prior work on semantic knowledge construction includes word sense disambiguafion techniques for text documents [9] 12][13]. Words in English may have more than one sense or meaning, for example plant, industrial plant and plant, living organism for the word plant . Word sense disambiguation (WSD) is the process of finding the correct sense of a word within a document, which is a long standing problem in Natural ....
.... words have only one sense (80 ) most words in text documents have more than one sense (80 ) 12] The two principles governing most wordsense disambiguation techniques are (1) that nearby words are semantically close or related and (2) that the sense of a word is often the same within a document [13]. In literature, there are unsupervised [9] 13] and supervised [12] approaches that often use WordNet as the electronic word sense lexicon. WordNet organizes English words into sets of synonyms (e.g. rock, stone ) and connects them with semantic relations (e.g. generalization) 10] There are ....
[Article contains additional citation context not shown here]
Yarowsky, D., "Unsupervised Word-sense disambiguation Rivaling Supervised Methods", Association of Computational Linguistics, 1995.
Learning Rules for Large-Vocabulary World Sense.. - Paliouras, al. (2000) (Correct)
....no correct tags against which to compare the results of the disambiguation. A compromise solution between supervised and unsupervised learning is the use of a small number of tagged examples, together with a large set of untagged data. Such partially supervised learning methods are presented in [23], 18] using rule learning and neural networks respectively. An important issue for any WSD learning algorithm is what features will be used to construct the disambiguation rules, i.e. what evidence is relevant for WSD. Since syntactic information is not considered useful for hard WSD tasks, ....
Yarowsky, D.: Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of the Annual Meeting of the Association for Computational Linguistics, (1995) 189-196
EAGLES LE3-4244: Preliminary Recommendations on.. - Sanfilippo.. (1999) (Correct)
....between these related senses in order to discover the most useful. This allowed Luk to produce a system which used the information in lexical resources as a way of reducing the amount of text needed in the training corpus. Another example of this approach is the unsupervised algorithm of Yarowsky [Yar95]. This takes a small number of seed definitions of the senses of some word (the seeds could be WordNet synsets or definitions from some lexicon) and uses these to classify the obvious cases in a corpus. Decision lists [Riv87] are then used to make generalisations based on the corpus instances ....
....such as to sweep something under the rug, phrasal verbs to spit up, compounds warning light. 9 Or some other derived tag set. 10 Especially considering that WordNet provides only two senses of stick together: S35 and S41. 198 CHAPTER 5. COMPONENT TECHNOLOGIES such as the one described in [Yar95] to choose the most appropriate meaning in context. How to evaluate the result on large corpora is still pending. Another step can be achieved by using the verb subcategorization frame together with selectional restriction for its arguments and shallow parsing. At RXRC we have developped a ....
D. Yarowsky. Unsupervised word-sense disambiguation rivaling supervised methods. In Proceedings of the 33rd Annual Meeting of the Association for Computational Lainguistics (ACL '95), pages 189--196, Cambridge, MA, 1995.
Active Learning with Multiple Views - Muslea (2002) (4 citations) (Correct)
No context found.
Yarowsky, David. 1995. Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of the 33rd annual meeting of the Association of Computational Linguistics, pages 189--196.
Gene Functional classification by Semi-supervised - Learning From Heterogeneous (Correct)
No context found.
D. Yarowsky. Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of the Annual Meeting of the Association for Computational Linguistics, pages 189--196, 1995.
An Augmented PAC Model for SemiSupervised Learning - Balcan, Blum (2005) (Correct)
No context found.
D. Yarowsky. Unsupervised word sense disambiguation rivaling supervised methods. In Meeting of the Association for Computational Linguistics, pages 189--196, 1995.
A PAC-style Model for Learning from Labeled and Unlabeled Data - Balcan, Blum (2005) (1 citation) (Correct)
No context found.
D. Yarowsky. Unsupervised word sense disambiguation rivaling supervised methods. In Meeting of the Association for Computational Linguistics, pages 189--196, 1995.
An Ontological-Semantic Framework for Text Analysis - Onyshkevych (1997) (1 citation) (Correct)
No context found.
Yarowsky, David (1995). "Unsupervised word sense disambiguation rivaling supervised methods ", in Proceedings of ACL95. Cambridge MA.
Annotating Concept Mention Patterns - Beata Beigman Klebanov (Correct)
No context found.
Yarowsky, David. 1995. Unsupervised Word Sense Disambiguation Rivaling Supervised Methods. Proceedings of ACL'95, 189--196.
Automated Induction of Sense in Context - Pustejovsky, HANKS, RUMSHISKY (2004) (Correct)
No context found.
D. Yarowsky. 1995. Unsupervised word sense disambiguation rivaling supervised methods. In Meeting of the Association for Computational Linguistics, pages 189--196.
Disambiguating Proteins, Genes, and RNA in Text: A.. - Hatzivassiloglou.. (2001) (Correct)
No context found.
Yarowsky, D. (1995). Unsupervised word sense disambiguation rivaling supervised methods. In Proc. 33rd ACL, pp. 189--196.
Towards Large-Scale, Open-Domain and Ontology-Based Named.. - Cimiano, Völker (2005) (Correct)
No context found.
D. Yarowsky. Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings od the Annual Meeting of the ACL, pages 189-- 196, 1995.
World Independent Context Pair Classification Model for . . . - Niu, Al. (2005) (Correct)
No context found.
Yarowsky, D. 1995. Unsupervised Word Sense Disambiguation Rivaling Supervised Methods. In Proceedings of ACL 1995.
Multi-View Hidden Markov Perceptrons - Brefeld, Büscher, Scheffer (Correct)
No context found.
D. Yarowsky. Unsupervised word sense disambiguation rivaling supervised methods. In Proc. of the Annual Meeting of the Association for Comp. Ling., 1995.
Predicate Preserving Parsing - Parikh, Khot, Dave, Bhattacharyya (2004) (Correct)
No context found.
Yarowsky, D., 1995. Unsupervised word sense disambiguation rivalling supervised methods. In Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics, pages 189-- 196, Cambridge, MA.
Analyzing the Effectiveness and Applicability Of Co-Training - Nigam, Ghani (2000) (9 citations) (Correct)
No context found.
D. Yarowsky. Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of ACL-95, 1995.
Learning Browsing Behavior Model for Web Recommendation - Zhu (2003) (Correct)
No context found.
D. Yarowsky. Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics, pages 189--196, Cambridge, MA, 1995.
Learning Translations from Comparable Corpora - Talbot (2003) (Correct)
No context found.
Yarowsky, D. (1995). Unsupervised word sense disambiguation rivaling supervised methods. In 33rd Meeting of the Association for Computational Linguistics, pages 189--196.
Exploiting Hidden Meanings Using Bilingual Text - Resnik (2004) (Correct)
No context found.
Yarowsky, D.: Unsupervised word sense disambiguation rivaling supervised methods. In: Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics, Cambridge, MA, Association for Computational Linguistics (1995) 189-196
The Role of Non-Ambiguous Words in Natural Language.. - Rada Mihalcea Department (2003) (1 citation) (Correct)
No context found.
, pages 189-- 196, Cambridge, MA, 1995 1995.
Learning Translations from Comparable Corpora - Talbot (2003) (Correct)
No context found.
Yarowsky, D. (1995). Unsupervised word sense disambiguation rivaling supervised methods. In 33rd Meeting of the Association for Computational Linguistics, pages 189--196.
Reasoning with Output from Parsing Using World Knowledge - Hunter, Marten (2000) (Correct)
No context found.
D Yarowsky. Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of the 32nd Annual Meeting of the Association of Computational Lingustics, pages 189--196, 1995. 36
A Highly Accurate Bootstrapping Algorithm For Word Sense.. - Mihalcea, Moldovan (2001) (1 citation) (Correct)
No context found.
Yarowsky, D. Unsupervised word sense disambiguation rivaling supervised methods. Proceedings of the 33rd Annual Meeting of the Association of Computational Linguistics (ACL-95), pages 189-196, Cambridge, MA, 1995.
First 50 documents Next 50
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC