Centering: a framework for modeling the local coherence of discourse
Computational Linguistics
Assessing agreement on classification tasks: the kappa statistic
Computational Linguistics
ECAI '96 Workshop on Dialogue Processing in Spoken Language Systems
Dialogue Structure Influence Over Anaphora Resolution
MICAI '00 Proceedings of the Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence
The reliability of a dialogue structure coding scheme
Computational Linguistics
Functional centering: grounding referential coherence in information structure
Computational Linguistics
A preliminary model of centering in dialog
ACL '98 Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 2
Anaphor resolution in unrestricted texts with partial parsing
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Providing a unified account of definite noun phrases in discourse
ACL '83 Proceedings of the 21st annual meeting on Association for Computational Linguistics
The representation and use of focus in a system for understanding dialogs
IJCAI'77 Proceedings of the 5th international joint conference on Artificial intelligence - Volume 1
Hi-index | 0.00 |
This paper shows an algorithm to relate noun phrase antecedents to 3rd person personal pronouns, possessive pronouns, demonstrative pronouns, and adjectival anaphora. This algorithm is based on the annotation scheme of dialogue structure within the combination of several kinds of knowledge (including lexical, morphological and syntactic knowledge). The algorithm has been applied to Spanish dialogues and its evaluation was carried out on a dialogue corpus. This corpus consist of 40 transcribed dialogues that are conversations between the telephone operator of a railway company and a user of the company. After this experiment a success rate of 73.8% was obtained in pronominal anaphora and 78.9% in adjectival anaphora. The implementation was performed using LPA Prolog.