Sciweavers

78 search results - page 10 / 16
» Determining Word Sense Dominance Using a Thesaurus
Sort
View
CORR
1998
Springer
96views Education» more  CORR 1998»
13 years 7 months ago
Similarity-Based Models of Word Cooccurrence Probabilities
Abstract. In many applications of natural language processing (NLP) it is necessary to determine the likelihood of a given word combination. For example, a speech recognizer may ne...
Ido Dagan, Lillian Lee, Fernando C. N. Pereira
ICASSP
2011
IEEE
12 years 11 months ago
Automatically finding semantically consistent n-grams to add new words in LVCSR systems
This paper presents a new method to automatically add n-grams containing out-of-vocabulary (OOV) words to a baseline language model (LM), where these n-grams are sought to be gram...
Gwénolé Lecorvé, Guillaume Gr...
NAACL
2003
13 years 8 months ago
Monolingual and Bilingual Concept Visualization from Corpora
e by placing terms in an abstract ‘information space’ based on their occurrences in text corpora, and then allowing a user to visualize local regions of this information space....
Dominic Widdows, Scott Cederberg
ICCV
1995
IEEE
13 years 11 months ago
Task-Oriented Generation of Visual Sensing Strategies
This paper describes a method of systematically generating visual sensing strategies based on knowledge of the assembly task to be performed. Since visual sensing is usually perfo...
Jun Miura, Katsushi Ikeuchi
CSL
2004
Springer
13 years 7 months ago
HyperLex: lexical cartography for information retrieval
This article describes an algorithm called HyperLex that is capable of automatically determining word uses in a textbase without recourse to a dictionary. The algorithm makes use ...
Jean Véronis