Anaphora Resolution in Dialogue: System ...
Document type :
Communication dans un congrès avec actes
Title :
Anaphora Resolution in Dialogue: System Description (CODI-CRAC 2022 Shared Task)
Author(s) :
Anikina, Tatiana [Auteur]
Skachkova, Natalia [Auteur]
Renner, Joseph [Auteur]
Machine Learning in Information Networks [MAGNET]
Inria Lille - Nord Europe
Trivedi, Priyansh [Auteur]
Machine Learning in Information Networks [MAGNET]
Semantic Analysis of Natural Language [SEMAGRAMME]
Skachkova, Natalia [Auteur]
Renner, Joseph [Auteur]
Machine Learning in Information Networks [MAGNET]
Inria Lille - Nord Europe
Trivedi, Priyansh [Auteur]
Machine Learning in Information Networks [MAGNET]
Semantic Analysis of Natural Language [SEMAGRAMME]
Scientific editor(s) :
Juntao Yu
Sopan Khosla
Ramesh Manuvinakurike
Lori Levin
Vincent Ng
Massimo Poesio
Michael Strube
Carolyn Rose
Sopan Khosla
Ramesh Manuvinakurike
Lori Levin
Vincent Ng
Massimo Poesio
Michael Strube
Carolyn Rose
Conference title :
Proceedings of the CODI-CRAC 2022 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue
City :
Gyeongju
Country :
Corée du Sud
Start date of the conference :
2022-10-16
Publisher :
Association for Computational Linguistics
HAL domain(s) :
Informatique [cs]/Informatique et langage [cs.CL]
Informatique [cs]/Apprentissage [cs.LG]
Informatique [cs]/Apprentissage [cs.LG]
English abstract : [en]
We describe three models submitted for the CODI-CRAC 2022 shared task. To perform identity anaphora resolution, we test several combinations of the incremental clustering approach based on the Workspace Coreference System ...
Show more >We describe three models submitted for the CODI-CRAC 2022 shared task. To perform identity anaphora resolution, we test several combinations of the incremental clustering approach based on the Workspace Coreference System (WCS) with other coreference models. The best result is achieved by adding the "cluster merging" version of the coref-hoi model, which brings up to 10.33% improvement 1 over vanilla WCS clustering. Discourse deixis resolution is implemented as multi-task learning: we combine the learning objective of corefhoi with anaphor type classification. We adapt the higher-order resolution model introduced in Joshi et al. (2019) for bridging resolution given gold mentions and anaphors.Show less >
Show more >We describe three models submitted for the CODI-CRAC 2022 shared task. To perform identity anaphora resolution, we test several combinations of the incremental clustering approach based on the Workspace Coreference System (WCS) with other coreference models. The best result is achieved by adding the "cluster merging" version of the coref-hoi model, which brings up to 10.33% improvement 1 over vanilla WCS clustering. Discourse deixis resolution is implemented as multi-task learning: we combine the learning objective of corefhoi with anaphor type classification. We adapt the higher-order resolution model introduced in Joshi et al. (2019) for bridging resolution given gold mentions and anaphors.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- document
- Open access
- Access the document
- 2022.codi-crac.2.pdf
- Open access
- Access the document
- 2301.02113
- Open access
- Access the document
- document
- Open access
- Access the document
- 2022.codi-crac.2.pdf
- Open access
- Access the document