Filters








466 Hits in 5.0 sec

Roget's Thesaurus as a Lexical Resource for Natural Language Processing [article]

Mario Jarmasz
2012 arXiv   pre-print
Computational linguists have employed Roget's for almost 50 years in Natural Language Processing, however hesitated in accepting Roget's Thesaurus because a proper machine tractable version was not available  ...  Inspired by WordNet's success, we propose as an alternative a similar resource, based on the 1987 Penguin edition of Roget's Thesaurus of English Words and Phrases.  ...  Jean-Pierre Corriveau, Carleton University 1 Introduction Lexical Resources for Natural Language Processing Natural Language Processing (NLP) applications need access to vast numbers of words and phrases  ... 
arXiv:1204.0140v1 fatcat:2oyur3xy6zdmdd6wu2rci2h2cu

Not as Easy as It Seems: Automating the Construction of Lexical Chains Using Roget's Thesaurus [chapter]

Mario Jarmasz, Stan Szpakowicz
2003 Lecture Notes in Computer Science  
The resulting lexical chains are a means of identifying cohesive regions in a text, with applications in many natural language processing tasks, including text summarization.  ...  We discuss the building of lexical chains using an electronic version of Roget's Thesaurus. We implement a variant of the original algorithm, and explain the necessary design decisions.  ...  Acknowledgments We thank Terry Copeck for having prepared the stop list used in building the lexical chains.  ... 
doi:10.1007/3-540-44886-1_48 fatcat:qjwekajrnvhxthjirrky4ocgbe

Automatically Expanding the Lexicon of Roget's Thesaurus [chapter]

Alistair Kennedy
2010 Lecture Notes in Computer Science  
I propose to build and evaluate a system for automatically updating the lexicon of Roget's Thesaurus. Roget's has been shown to lend itself well to many Natural Language Processing tasks.  ...  One of the factors limiting Roget's use is that the only publicly available version of Roget's is from 1911 and is sorely in need of an updated lexicon.  ...  Stan Szpakowicz for his guidance.  ... 
doi:10.1007/978-3-642-13059-5_58 fatcat:n6ofzopydjhx5dvgbeyqasfyka

Evaluation of automatic updates of Roget's Thesaurus

Alistair Kennedy, Stan Szpakowicz
2014 Journal of Language Modelling  
Thesauri and similarly organised resources attract increasing interest of Natural Language Processing researchers. Thesauri age fast, so there is a constant need to update their vocabulary.  ...  This work presents a tuneable method of measuring semantic relatedness, trained on Roget's Thesaurus, which generates lists of terms related to words not yet in the Thesaurus.  ...  Natural Language Processing (NLP).  ... 
doi:10.15398/jlm.v2i1.78 fatcat:vmj27sjvrvdszjl7scmm3ijopm

Building A Thesaurus Using LDA-Frames

Jirí Materna
2012 Recent Advances in Slavonic Natural Languages Processing  
In this paper we present a new method for measuring semantic relatedness of lexical units, which can be used to generate a thesaurus automatically.  ...  The method is based on a comparison of probability distributions of semantic frames generated using the LDA-frames algorithm.  ...  In comparison to Roget's thesaurus, which is primarily intended to be used by humans, WordNet is more often utilized in natural language processing taks.  ... 
dblp:conf/raslan/Materna12 fatcat:7dnx2gs2kzcunmaa3k6ruc37qe

Roget's thesaurus and semantic similarity [chapter]

Mario Jarmasz, Stan Szpakowicz
2004 Current issues in linguistic theory  
We have implemented a system that measures semantic similarity using a computerized 1987 Roget's Thesaurus, and evaluated it by performing a few typical tests.  ...  Our Roget's-based system gets correlations of .878 for the smaller and .818 for the larger list of noun pairs; this is quite close to the .885 that Resnik obtained when he employed humans to replicate  ...  We explain in detail the measures and the experiments, and draw a few conclusions. 2 Roget's Thesaurus Relations as a Measure of Semantic Distance Resnik (1995) claims that a natural way of calculating  ... 
doi:10.1075/cilt.260.12jar fatcat:3feff4k7zjgq7kc4s2lwcikize

Using Roget's Thesaurus for Fine-grained Emotion Recognition

Saima Aman, Stan Szpakowicz
2008 International Joint Conference on Natural Language Processing  
One lexicon is automatically built using the classification system of Roget's Thesaurus, while the other consists of words extracted from WordNet-Affect.  ...  We experiment with corpus-based features as well as features derived from two emotion lexicons.  ...  Previous work has used lexical resources such as WordNet to automatically acquire emotion-related words for emotion classification experiments.  ... 
dblp:conf/ijcnlp/AmanS08 fatcat:api2wcmdcbhrvfmboz2rh6ce2i

Imparting Interpretability to Word Embeddings while Preserving Semantic Structure [article]

Lutfi Kerem Senel, Ihsan Utlu, Furkan Şahinuç, Haldun M. Ozaktas, Aykut Koç
2020 arXiv   pre-print
The predefined concepts are derived from an external lexical resource, which in this paper is chosen as Roget's Thesaurus.  ...  As an ubiquitous method in natural language processing, word embeddings are extensively employed to map semantic properties of words into a dense vector representation.  ...  The predefined concepts are derived from an external lexical resource, which in this paper is chosen as Roget's Thesaurus.  ... 
arXiv:1807.07279v3 fatcat:r4lf34zjajdidhiqbi274q46w4

Page 28 of Language Sciences Vol. , Issue 31 [page]

1974 Language Sciences  
I will digress for a moment to discuss the thesaurus-dictionary.  ...  As such it should perhaps be a first resource of anyone interested in the field phenomena of semantics.  ... 

A Supervised Method of Feature Weighting for Measuring Semantic Relatedness [chapter]

Alistair Kennedy, Stan Szpakowicz
2011 Lecture Notes in Computer Science  
The clustering of related words is crucial for a variety of Natural Language Processing applications. Many known techniques of word clustering use the context of a word to determine its meaning.  ...  We use Roget's Thesaurus as a source of training and evaluation data. This work is as a step towards adding new terms to Roget's Thesaurus automatically, and doing so with high confidence.  ...  Acknowledgments Our research is supported by the Natural Sciences and Engineering Research Council of Canada and the University of Ottawa.  ... 
doi:10.1007/978-3-642-21043-3_27 fatcat:rbrgtulrxbcldioefq5t6ralqe

Combining Lexical Resources for Contextual Synonym Expansion

Ravi Som Sinha, Rada Mihalcea
2009 Recent Advances in Natural Language Processing  
Overall, the results obtained through the combination of several resources exceed the current state-of-the-art when selecting the best synonym for a given target word, and place second when selecting the  ...  In this paper, we experiment with the task of contextual synonym expansion, and compare the benefits of combining multiple lexical resources using both unsupervised and supervised approaches.  ...  Roget's thesaurus Roget is a thesaurus of the English language, with words and phrases grouped into hierarchical classes.  ... 
dblp:conf/ranlp/SinhaM09 fatcat:uiwfz2ocnneo5fn2amxz6nsbia

Formally modeling and extending whole-language-scale semantic space

Sally Yeates Sedelow
1993 Behavoir research methods, instruments & computers  
For the analysis of continuous discourse in a wide range of corpora, it is essential both to model and to expand whole-language lexical resources (e.g., Roget's International Thesaurus), in order to make  ...  My presentation argues for the validity ofthis approach, with specific reference to a viable conceptual, whole-language, foundational lexicon, Roget's International Thesaurus (1962).  ...  As to the first of the gains in having a single generalpurpose thesaurus-that of not having to construct disjoint thesauri ab novo-our process is to make the thesaurus' representation of the English lexical  ... 
doi:10.3758/bf03204519 fatcat:ufmo27scjbc2xoa3fty44xuuua

Imparting interpretability to word embeddings while preserving semantic structure

Lütfi Kerem Şenel, İhsan Utlu, Furkan Şahinuç, Haldun M. Ozaktas, Aykut Koç
2020 Natural Language Engineering  
The predefined concepts are derived from an external lexical resource, which in this paper is chosen as Roget's Thesaurus.  ...  As a ubiquitous method in natural language processing, word embeddings are extensively employed to map semantic properties of words into a dense vector representation.  ...  Tolga Cukur (Bilkent University) for fruitful discussions. We would also like to thank the anonymous reviewers for their many comments which significantly improved the quality of our manuscript.  ... 
doi:10.1017/s1351324920000315 fatcat:odbepv3l7naqpn74des5pal5ea

Page 36 of Computational Linguistics Vol. 28, Issue 2 [page]

2002 Computational Linguistics  
Reversible machine translation: What to do when the languages don’t match up. In Tomek Strzalkowski, editor, Reversible Grammar in Natural Language Processing. Kluwer Academic, pages 321-364.  ...  Roget’s International Thesaurus. 5th edition. Near-Synonymy and Lexical Choice HarperCollins Publishers. Church, Kenneth Ward, William Gale, Patrick Hanks, Donald Hindle, and Rosamund Moon. 1994.  ... 

EVALUATING SEMANTIC SIMILARITY MEASURES FOR ENGLISH VERBS IN WORDNET AND THESAURI

Iryna Dilay, Mykhailo Bilynskyi
2016 NOZEMNA PHILOLOGIA  
thesaurus. © I.  ...  However, the measures, being predominantly of a non-linear character, fail to account for synonymy of words, as well as convey the principles of mental lexicon structuring, in particular the assymetry  ...  Introduction Measures of semantic similarity and relatedness between concepts are widely used in Natural Language Processing.  ... 
doi:10.30970/fpl.2016.129.593 fatcat:ttzngr5d2zggtnhvb7dxhnxhym
« Previous Showing results 1 — 15 out of 466 results