Filters








806 Hits in 4.8 sec

Automatic Word Sense Disambiguation Using Cooccurrence and Hierarchical Information [chapter]

David Fernandez-Amoros, Ruben Heradio Gil, Jose Antonio Cerrada Somolinos, Carlos Cerrada Somolinos
2010 Lecture Notes in Computer Science  
We use that information to expand sense glosses of the senses in WordNet and compare the similarity between the contexts vectors and the word sense vectors in a way similar to that used by Yarowsky and  ...  It is based on a combination of selectional preference measured over a large corpus and hierarchical information taken from WordNet, as well as some additional heuristics.  ...  For Senseval-2, we have combined word cooccurrence and hierarchical information as sources of disambiguation evidence [5] .  ... 
doi:10.1007/978-3-642-13881-2_6 fatcat:imb7m6bghva3xdabar2z2uebi4

Combining Unsupervised Lexical Knowledge Methods for Word Sense Disambiguation [article]

German Rigau, Jordi Atserias, Eneko Agirre
1997 arXiv   pre-print
This paper presents a method to combine a set of unsupervised algorithms that can accurately disambiguate word senses in a large, completely untagged corpus.  ...  Although most of the techniques for word sense resolution have been presented as stand-alone, it is our belief that full-fledged lexical ambiguity resolution should combine several information sources  ...  Country and Horacio Rodríguez in Catalonia.  ... 
arXiv:cmp-lg/9704007v1 fatcat:qlqcgxm5czhn5e57y6kk4wmzye

Combining unsupervised lexical knowledge methods for word sense disambiguation

German Rigau, Jordi Atserias, Eneko Agirre
1997 Proceedings of the 35th annual meeting on Association for Computational Linguistics -  
This paper presents a method to combine a set of unsupervised algorithms that can accurately disambiguate word senses in a large, completely untagged corpus.  ...  Although most of the techniques for word sense resolution have been presented as stand-alone, it is our belief that full-fledged lexical ambiguity resolution should combine several information sources  ...  Country and Horacio Rodr~guez in Catalonia.  ... 
doi:10.3115/976909.979624 dblp:conf/acl/RigauAA97 fatcat:hyjbadnu4fbslmrwze2twpwuv4

Page 1997 of Computational Linguistics Vol. 24, Issue 1 [page]

1998 Computational Linguistics  
Using WordNet to disambiguate word senses for text retrieval. In Proceedings of SIGIR ‘93, pages 171-180. Walker, Donald E. and Robert A. Amsler. 1986.  ...  Introduction to Modern Information Retrieval. McGraw-Hill, New York. Sanderson, Mark. 1994. Word sense disambiguation and information retrieval. In Proceedings of SIGIR ‘94, pages 142-151.  ... 

Using big data to support automatic Word Sense Disambiguation

Giovanni Simonini, Francesco Guerra
2014 2014 International Conference on High Performance Computing & Simulation (HPCS)  
In this paper, we propose an approach to automatically build a generic sense inventory (called iSC) to be used as a reference for disambiguation.  ...  Word Sense Disambiguation (WSD) usually relies on data structures built upon the words to be disambiguated. This is a time-consuming process that requires a huge computational effort.  ...  AUTOMATIC WORD SENSE DISAMBIGUATION, LIMITS AND SOLUTIONS Automatic WSD addresses the problem of identifying which sense is more suitable for a polysemic word in a context, dividing the occurrences of  ... 
doi:10.1109/hpcsim.2014.6903701 dblp:conf/hpcs/SimoniniG14 fatcat:z64cfhmdzbcyheqrjyeioxuhei

Learning similarity-based word sense disambiguation from sparse data [article]

Yael Karov, Shimon Edelman
1996 arXiv   pre-print
We describe a method for automatic word sense disambiguation using a text corpus and a machine-readable dictionary (MRD). The method is based on word similarity and context similarity measures.  ...  A new instance of a polysemous word is assigned the sense associated with the typical usage most similar to its context.  ...  Introduction Word Sense Disambiguation (WSD) is the problem of assigning a sense to an ambiguous word, using its context.  ... 
arXiv:cmp-lg/9605009v2 fatcat:foj2lowcpnhe7mv56krunbhh2u

Word Sense Disambiguation using Conceptual Density [article]

Eneko Agirre, German Rigau
1996 arXiv   pre-print
The results of the experiments have been automatically evaluated against SemCor, the sense-tagged version of the Brown Corpus.  ...  This paper presents a method for the resolution of lexical ambiguity of nouns and its automatic evaluation over the Brown Corpus.  ...  Acknowledgements We wish to thank all the staff of the Computer Research Laboratory and specially Jim Cowie, Joe Guthtrie, Louise Guthrie and David Farwell.  ... 
arXiv:cmp-lg/9606007v1 fatcat:4agvqv6p5jfw7p7qkmcg3ci6qu

Contextual word similarity and estimation from sparse data

Ido Dagan, Shaul Marcus, Shaul Markovitch
1995 Computer Speech and Language  
A background survey is included, covering issues of lexical cooccurrence, data sparseness and smoothing, word similarity and clustering, and mutual information.  ...  These analogies are based on the assumption that similar word cooccurrences have similar values of mutual information.  ...  Acknowledgements We w ould like to thank Alon Itai for help in initiating this research, and Ken Church for helpful comments on an earlier draft of this paper.  ... 
doi:10.1006/csla.1995.0008 fatcat:3sblkcheqbbkldgtlyy4fk5mgy

Contextual word similarity and estimation from sparse data

Ido Dagan, Shaul Marcus, Shaul Markovitch
1993 Proceedings of the 31st annual meeting on Association for Computational Linguistics -  
A background survey is included, covering issues of lexical cooccurrence, data sparseness and smoothing, word similarity and clustering, and mutual information.  ...  These analogies are based on the assumption that similar word cooccurrences have similar values of mutual information.  ...  Acknowledgements We w ould like to thank Alon Itai for help in initiating this research, and Ken Church for helpful comments on an earlier draft of this paper.  ... 
doi:10.3115/981574.981596 dblp:conf/acl/DaganMM93 fatcat:rv3mhgxbzbh3xg5o5n6bpyuuay

Similarity-Based Models of Word Cooccurrence Probabilities [article]

Ido Dagan, Lillian Lee, Fernando C. N. Pereira
1998 arXiv   pre-print
We also compare four similarity-based estimation methods against back-off and maximum-likelihood estimation methods on a pseudo-word sense disambiguation task in which we controlled for both unigram and  ...  In this work we propose a method for estimating the probability of such previously unseen word combinations using available information on "most similar" words.  ...  model, and Andrej Ljolje and Michael Riley for providing word lattices for our speech recognition evaluation.  ... 
arXiv:cs/9809110v1 fatcat:hb3aaoyt3rfz3drt27lhrvxm6q

Exploiting Thesauri and Hierarchical Categories in Cross-Language Information Retrieval [chapter]

Fatiha Sadat, Masatoshi Yoshikawa, Shunsuke Uemura
2002 Lecture Notes in Computer Science  
We propose a model using multiple sources for query reformulation and expansion to select expansion terms and retrieve information needed by a user.  ...  A combination to a dictionary-based translation and statistical-based disambiguation is indispensable to overcome translation's ambiguity.  ...  disambiguation and select best target translations, • Adding domain keywords to the original query and then selecting thesaurus word senses, to avoid wrong sense disambiguation, is considered as an effective  ... 
doi:10.1007/3-540-46154-x_18 fatcat:23tmssl6pfcl5probpxxr44c6i

Word Sense Disambiguation by Relative Selection [chapter]

Hee-Cheol Seo, Hae-Chang Rim, Myung-Gil Jang
2005 Lecture Notes in Computer Science  
Only one cooccurrence frequency matrix is utilized to efficiently disambiguate senses of many target words.  ...  This paper describes a novel method for a word sense disambiguation that utilizes relatives (i.e. synonyms, hypernyms, meronyms, etc in WordNet) of a target word and raw corpora.  ...  The corpora, which have sense information of all words, have been built recently, but are not large enough to provide sufficient disambiguation information of the all words.  ... 
doi:10.1007/11562214_80 fatcat:esazdknon5avzivpvfq5mw2jhe

An Insight into Word Sense Disambiguation Techniques

Harsimran Singh, Vishal Gupta
2015 International Journal of Computer Applications  
This paper presents various techniques used in the area of Word Sense Disambiguation (WSD).  ...  previously semantically annotated corpus; Unsupervised approaches that form cluster occurrences of words.  ...  INTRODUCTION Word Sense Disambiguation is the determination of sense of a particular word used in a particular context.  ... 
doi:10.5120/20888-3666 fatcat:igoikbgvavfetfptwinwbz5z7y

Biomedical word sense disambiguation with ontologies and metadata: automation meets accuracy

Dimitra Alexopoulou, Bill Andreopoulos, Heiko Dietze, Andreas Doms, Fabien Gandon, Jörg Hakenberg, Khaled Khelif, Michael Schroeder, Thomas Wächter
2009 BMC Bioinformatics  
Another useful source of information for disambiguation are metadata. Here, we systematically compare three approaches to word sense disambiguation, which use ontologies and metadata, respectively.  ...  Classical approaches to word sense disambiguation use co-occurring words or terms.  ...  An implementation of the Porter stemmer is used [44] and as features we select n-tuples of word stems and meta information of the document, such as the journal and title words and the publication period  ... 
doi:10.1186/1471-2105-10-28 pmid:19159460 pmcid:PMC2663782 fatcat:gv64eqpyvna6jmfzxugdltml3m

Evaluating Feature Extraction Methods for Knowledge-based Biomedical Word Sense Disambiguation

Sam Henry, Clint Cuffy, Bridget McInnes
2017 BioNLP 2017  
In this paper, we present an analysis of feature extraction methods via dimensionality reduction for the task of biomedical Word Sense Disambiguation (WSD).  ...  We modify the vector representations in the 2-MRD WSD algorithm, and evaluate four dimensionality reduction methods: Word Embeddings using Continuous Bag of Words and Skip Gram, Singular Value Decomposition  ...  Introduction W ord Sense Disambiguation (WSD) is the task of automatically identifying the intended sense (or concept) of an ambiguous word based on the context in which the word is used.  ... 
doi:10.18653/v1/w17-2334 dblp:conf/bionlp/HenryCM17 fatcat:s27v3blmy5ebtepd73peqe54vm
« Previous Showing results 1 — 15 out of 806 results