| E. Voorhees. Using WordNet to disambiguate word senses for text retrieval. In SIGIR 1993. |
.... of dictionaries, morphological analysis, bilingual corpera, and Wordnet [70] While disambiguation of individual terms can often be accomplished with a high degree of precision [84] it has rarely led to improved performance for an IR system and has often produced a significant drop in performance [80]. Sanderson [70] runs a simulation experiment where he replaces groups of words at random with a pseudo word to introduce artificial ambiguity and then measures the change in performance of the IR system. He finds that one can add a large amount of ambiguity before performance is extensively ....
Ellen M. Voorhees. Using wordnet to disambiguate word senses for text retrieval. In Proc. 16th Int'l Conference on R&D in IR (SIGIR), pages 171--180, 1993.
....effects the performance of the II system negatively. He proves that in order to be of any practical use and in order to improve the performance of an II system, a disambiGuation algorithm has to work with at least 90 accuracy. One thin G that attracts our attention about the previous work [22] [25] is that even the most extensive research in the application of word sense disambiGuation to information retrieval has focused on retrievin G disambiGuated information from disambiGuated documents. We believe that focusin G on disambiGuatin G the query rather than the documents would be more ....
....with regard to that query, tend to use the words in the same sense as the query. Therefore they concluded that WSD did not have a very important impact on IR, but that 18 disambiguation could be beneficial to IR when there were a few words in common between the query and the document. Voorhees [22] presented a large scale test of applying word sense disambiguation to an IR system. For this test, Voorhees built an automatic indexer, which could also be called a sense disambiguator, based on the is a relations contained within WORDNET thesaurus [12] and a set of nouns contained in a text. The ....
[Article contains additional citation context not shown here]
E. M. Voorhees. Using WORDNET to Disambiguate Word Senses for Text Retrieval. In SIGIR '93, Proceedings of the sixteenth annual international ACM SIGIR conference on Research and Development in Information Retrieval, pages 171-180.
....concept classification information, seems very promis Approximated by estimating the probability of occurence of a term in a corpus. This is attributed to the fact that both captions and queries are short, since it has been shown that the same does not apply in text retrieval applications [18]. ing for image caption retrieval according to the thorough evaluation experiments reported [4] Research on extraction based text categorization point to the same direction too [10] In Rilo# et al. 1999) domain dependent extraction patterns and semantic features associated with role fillers ....
E. Voorhees. Using wordnet to disambiguate word senses for text retrieval. In Proceedings of the 16th ACM SIGIR Conference, pages 171--180, 1993. 18
....are recent attempts to index the document based on conceptual terms. However the knowledge sources are usually incomplete. As a result, past research reveals that although using conceptual terms for document indexing can solve some of the problems, it cannot outperform the word stem based model [3,4,5,6]. To remedy the incompleteness of the knowledge sources, we propose a phrase based indexing model where we parse a document into phrases based on the conceptual terms in domain specific knowledge sources, and calculate the similarity between two documents using both the similarity between the ....
....u appears in , the more important u is in . On the other hand, the more documents u belongs to, the less disambiguating power it has, and thus the less important it is. Word stems are widely used as index terms. To improve retrieval accuracy, it is natural to replace word stems with concepts [3,4,5,6,8] or multiple word combinations [9,10] However, previous research showed not only no improvements, but degradation in retrieval accuracy when concepts were used in document retrieval [3,4,5,6] except when documents were very short [8] When properly used, multiple word combinations were shown to ....
[Article contains additional citation context not shown here]
E.M. Voorhees. Using WordNet to Disambiguate Word Sense for Text Retrieval. In Proc. 16 ACM-SIGIR., 171-180, 1993
....to the query vector. Word stems are widely used as index terms. To improve retrieval accuracy, it is natural to replace word stems with concepts. However, previous research showed not only no improvements, but degradation in retrieval accuracy when concepts were used in document retrieval [2,3,4,5] except when documents were very short [6] Replacing word stems with multiple word combinations was also studied [7] In the following sections, we first propose to use phrases instead of word stems as index terms. A phrase is a string of words used to represent concepts. Since some ....
E.M. Voorhees. Using WordNet to Disambiguate Word Sense for Text Retrieval. In Proc. 16 ACMSIGIR. , 171-180, 1993
....used by the natural language processing (NLP) community. The information contained in WordNet can be used in a lot of reasoning tasks to solve a set of NL problems (Part of speech tagging [ Segond et al. 1997 ] PP attachment [ Krymolowski and Roth, 1998 ] WSD [ Resnik, 1997, Sussna, 1993, Voorhees, 1993, Wiebe et al. 1998 ] information extraction [ Chai and Biermann, 1997 ] Nevertheless, no reasoning procedure is provided by WordNet itself. It only provides information. Mainly it provides ontological information about concepts that correspond to word senses. Every time we want to ....
....solution must provide a mechanism to reason with the information provided by WordNet. There are two di erent approaches in using WordNet information. The rst one consists in applying a generic reasoning model based on taxonomic information [ Agirre and Rigau, 1996, Resnik, 1997, Sussna, 1993, Voorhees, 1993 ] This approach is normally related to unsupervised learning techniques. The second approach uses WordNet as a hierarchy of classes of objects (where a class corresponds to a WordNet sense or synset) where new information stating the behaviour of WordNet classes is added [ Ng and Lee, 1996, ....
E. Voorhees. Using wordnet to disambiguate word senses for text retrieval. In Proceedings of the 16th Annual ACM SIGIR Conference on Research and Development in Information Retrieval, pages 171-180, Pittsburgh, 1993. 12
....discussing carcinoma. Concepts have been proposed to replace word stems to index documents, so that different expressions are matched to the same concept. However, because knowledge sources are often incomplete in defining concepts, concept based indexing has not achieved significant improvement [9, 10, 11]. In this paper, we propose a phrase based indexing technique that uses both word stems and concepts to index a medical document. This technique compensates for the incompleteness of concepts using word stems, and greatly enhances our system s capability to correlate documents from different ....
E.M. Voorhees. Using WordNet to disambiguate word sense for text retrieval. In Proceedings of ACM SIGIR '93, 1993.
....information retrieval system [19] to retrieve the documents. Through her experiments, Voorhees succeeded in improving the system performance on only short queries with little or no significant improvement for long queries. She further tried to use WordNet as a tool for word sense disambiguation [26] and applied it to text retrieval, but the performance of retrieval was degraded. Smeaton [25] tried to expand the queries of the TREC4 collection with various strategies of weighting expansion terms, along with manual and automatic word sense disambiguation techniques. Unfortunately all ....
E.M. Voorhees. Using WordNet to disambiguate word senses for text retrieval. In Proceedings of the 16th ACM-SIGIR Conference, pp. 171--180, 1993.
....to be merged into a single unit. If a new thesams can indeed be served by merging two or more existing thesauri, then a merger perhaps is likely to be more efficient than producing the thesams from scratch. The simplest approach is to reuse existing online lexicographic databases, such as WordNet [19, , 20] Longman s subject codes [21] or using the per arranged list of terms like table of content or book indexing [22] to aid in the construction. In constructing a system that has to conduct a fair amount of semantic understanding, a thesams is known to be very useful tool. International Press ....
E. M Voorhees, "Using WordNet to Disambiguate Word Sense for Text Retrieval", Proc ACM SIGIR'93, Pittsburgh, 1993, 171-180.
No context found.
E. Voorhees. Using WordNet to disambiguate word senses for text retrieval. In SIGIR 1993.
No context found.
: Ellen M. Voorhees; Using WordNet to Disambiguate Word Sense for Text Retrieval; ACMSIGIR '93; pp. pp. 171-180; Pittsburg, PA, USA; June 1993.
No context found.
E. Voorhees. Using WordNet to disambiguate word senses for text retrieval. In Proceedings of SIGIR'93, 1993.
No context found.
E. Voorhees. 1993. Using wordnet to disambiguate word senses for text retrieval. In Proceedings of the 16th annual international ACM SIGIR conference, Pittsburgh, PA.
No context found.
Ellen M. Voorhees. 1993. Using wordnet to disambiguate word senses for text retrieval. In Proceedings SIGIR'93 Pittsburgh, PA, USA.
No context found.
Voorhees, E. M. Using WordNet to disambiguate word sense for text retrieval. In Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval (Pittsburgh, PA USA, 1993), R. Korfhage, E. Rasmussen, and P. Willet, Eds., pp. 171--180. 15
No context found.
E. M. Voorhees. Using WordNet to disambiguate word sense for text retrieval. In Proceedings of the Sixteenth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 171--180, 1993.
No context found.
, pp. 171-180, 1993.
No context found.
E. Voorhees, Using wordnet to disambiguate word senses for text retrieval, In Proceedings of the 16th ACM SIGIR Conference, 1993, pp. 171 -- 180.
No context found.
E. M. Voorhees. Using wordnet to disambiguate word senses for text retrieval. In R. Korfhage, E. Rasmussen, and P. Willett, editors, Proceesings of the 16th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 171--180. ACM Press, 1993. Pittsburgh, PA USA, June 27 - July 1.
No context found.
E. M. Voorhees. Using WordNet to disambiguate words senses for text retrieval. Proceedings of the 16 Annual International Conference on Research and Development in Information Retrieval (SIGIR'93), 171-180, 1993.
No context found.
E. M. Voorhees. Using WordNet to disambiguate word sense for text retrieval. In Proceedings of the Sixteenth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 171--180, 1993.
No context found.
Voorhees, E.M.: Using WordNet to Disambiguate Word Senses for Text Retrieval. Proceedings of the Sixteenth Annual International ACM SIGIR conference on Research and Development in Information Retrieval (1993) 171 -- 180
No context found.
: Ellen M. Voorhees; Using WordNet to Disambiguate Word Sense for Text Retrieval; ACMSIGIR '93; pp. pp. 171-180; Pittsburg, PA, USA; June 1993.
No context found.
Voorhees, E.: Using WordNet to Disambiguate Word Senses for Text Retrieval. In: Proceedings of the 16th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Pittsburgh (1993) 171-180
No context found.
Voorhees, Ellen. M. 1993. "Using WordNet to Disambiguate Word Senses for Text Retrieval," in Proceedings of SIGIR'93. 295
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