Computational Approach to Anaphora Resolution in Spanish Dialogues

  title={Computational Approach to Anaphora Resolution in Spanish Dialogues},
  author={Patricio Mart{\'i}nez-Barco and Manuel Palomar},
  journal={J. Artif. Intell. Res.},
This paper presents an algorithm for identifying noun-phrase antecedents of pronouns and adjectival anaphors in Spanish dialogues. We believe that anaphora resolution requires numerous sources of information in order to nd the correct antecedent of the anaphor. These sources can be of diierent kinds, e.g., linguistic information, discourse/dialogue structure information, or topic information. For this reason, our algorithm uses various diierent kinds of information (hybrid information). The… CONTINUE READING

From This Paper

Results and topics from this paper.

Key Quantitative Results

  • According to this study, 95.9% of antecedents were located in the proposed space, a precision of 81.3% was obtained for pronominal anaphora resolution, and 81.5% for adjectival anaphora.


Publications referenced by this paper.
Showing 1-10 of 32 references

Discourse Structure and Anaphora : an Empirical Study

View 4 Excerpts
Highly Influenced

Dialogue acts, synchronising units and anaphora

M. Eckert, M. Strube
View 6 Excerpts
Highly Influenced

Anaphora resolution in unrestricted texts

A. Ferr andez, M. Palomar, L. Moreno
View 7 Excerpts
Highly Influenced

Draft of DAMSL: Dialog act markup in several layers

J. Allen, M. Core
View 5 Excerpts
Highly Influenced

Algoritmo de resoluci on de la an afora pronominal en di alogos

P. Mart nez-Barco
View 4 Excerpts
Highly Influenced

An Algorithm for Pronominal Anaphora Resolution

Computational Linguistics • 1994
View 4 Excerpts
Highly Influenced

Evaluation of pronoun resolution algorithm for Spanish

P Mart nez-Barco
View 1 Excerpt
Highly Influenced

Statistical Models for Topic Segmentation

ACL • 1999
View 3 Excerpts
Highly Influenced

Spontaneous-Speech Dialogue System in Limited Domains

Basurde Project
CICYT • 1998
View 3 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…