This paper presents and evaluates models created according to a schema that provides a description of the joint distribu-tion of the values of sense tags and contextual features that is potentially applicable to a wide range of content words. The models are evaluated through a series of experiments, the results of which suggest that the schema is particularly well suited to nouns but that it is also applicable to words in other syntactic categories. 1
There has been a tradition of combining differ-ent knowledge sources in Artificial Intelligence rese...
We present an unsupervised learning strategy for word sense disambiguation (WSD) that exploits multi...
Word Sense Disambiguation (WSD) is traditionally considered an AI-hard problem. A break-through in t...
This paper presents and evaluates models created according to a schema that provides a description o...
Most word representation methods assume that each word owns a single semantic vec-tor. This is usual...
Sense tagging, the automatic assignment of the appropriate sense from some lexicon to each of the wo...
Word sense disambiguation algorithms, with few exceptions, have made use of only one lexical knowled...
There has been a tradition of combining different knowledge sources in Artificial Intelligence resea...
Word sense disambiguation (WSD) is a computational linguistics task likely to benefit from the tradi...
Current research in knowledge-based Word Sense Disambiguation (WSD) indicates that performances depe...
Word Sense Disambiguation (WSD) aims at making explicit the semantics of a word in context by identi...
[[abstract]]©1998 ACL-Word sense disambiguation for unrestricted text is one of the most difficult t...
Verbs that can have more than one meaning pose problems for Natural Language Processing (NLP) applic...
Identifying the correct sense of a word in context is crucial for many tasks in natural language pro...
In this paper we present a maximum entropy Word Sense Disambiguation system we developed which per...
There has been a tradition of combining differ-ent knowledge sources in Artificial Intelligence rese...
We present an unsupervised learning strategy for word sense disambiguation (WSD) that exploits multi...
Word Sense Disambiguation (WSD) is traditionally considered an AI-hard problem. A break-through in t...
This paper presents and evaluates models created according to a schema that provides a description o...
Most word representation methods assume that each word owns a single semantic vec-tor. This is usual...
Sense tagging, the automatic assignment of the appropriate sense from some lexicon to each of the wo...
Word sense disambiguation algorithms, with few exceptions, have made use of only one lexical knowled...
There has been a tradition of combining different knowledge sources in Artificial Intelligence resea...
Word sense disambiguation (WSD) is a computational linguistics task likely to benefit from the tradi...
Current research in knowledge-based Word Sense Disambiguation (WSD) indicates that performances depe...
Word Sense Disambiguation (WSD) aims at making explicit the semantics of a word in context by identi...
[[abstract]]©1998 ACL-Word sense disambiguation for unrestricted text is one of the most difficult t...
Verbs that can have more than one meaning pose problems for Natural Language Processing (NLP) applic...
Identifying the correct sense of a word in context is crucial for many tasks in natural language pro...
In this paper we present a maximum entropy Word Sense Disambiguation system we developed which per...
There has been a tradition of combining differ-ent knowledge sources in Artificial Intelligence rese...
We present an unsupervised learning strategy for word sense disambiguation (WSD) that exploits multi...
Word Sense Disambiguation (WSD) is traditionally considered an AI-hard problem. A break-through in t...