An algorithm for pronominal anaphora resolution
Computational Linguistics
Natural Language, Relevancy Ranking, and Common Sense
IEEE Intelligent Systems
Anaphor resolution in unrestricted texts with partial parsing
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Anaphora for everyone: pronominal anaphora resoluation without a parser
COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 1
University of Sheffield: description of the LaSIE system as used for MUC-6
MUC6 '95 Proceedings of the 6th conference on Message understanding
CogNIAC: high precision coreference with limited knowledge and linguistic resources
ANARESOLUTION '97 Proceedings of a Workshop on Operational Factors in Practical, Robust Anaphora Resolution for Unrestricted Texts
| Hi-index | 0.00 |
Tendencies in Natural Language Processing (NLP) systems go towards the study of the semantic knowledge that can be extracted from the words within a context. For this reason, semantic information addition is necessary for the definition of new NLP strategies. In this paper, a method oriented to pronominal anaphora resolution in Spanish is presented. This method is based on two ontologies, On and Ov, that define semantic concept branches for nouns and verbs respectively. Also, the method uses two relation sets in order to solve the anaphora. These sets are formed by semantic patterns that define the compatibility between a subject and its verb and verb and its complement, using the ontological concepts of their heads. The semantic behaviour provided by these patterns allows the identification of the noun phrase antecedents of a Spanish personal pronoun. This antecedent has the best compatibility ratio among all proposed antecedents of the anaphoric pronoun. This compatibility ratio is measured using the relation level between concepts in the ontological branch of each pair member.