Abstract
This paper presents a collaborative partitioning algorithm—a novel ensemble-based approach to coreference resolution. Starting from the all-singleton partition, we search for a solution close to the ensemble’s outputs in terms of a task-specific similarity measure. Our approach assumes a loose integration of individual components of the ensemble and can therefore combine arbitrary coreference resolvers, regardless of their models. Our experiments on the CoNLL dataset show that collaborative partitioning yields results superior to those attained by the individual components, for ensembles of both strong and weak systems. Moreover, by applying the collaborative partitioning algorithm on top of three state-of-the-art resolvers, we obtain the best coreference performance reported so far in the literature (MELA v08 score of 64.47).- Anthology ID:
- K17-1007
- Volume:
- Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)
- Month:
- August
- Year:
- 2017
- Address:
- Vancouver, Canada
- Venue:
- CoNLL
- SIG:
- SIGNLL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 47–57
- Language:
- URL:
- https://aclanthology.org/K17-1007
- DOI:
- 10.18653/v1/K17-1007
- Cite (ACL):
- Olga Uryupina and Alessandro Moschitti. 2017. Collaborative Partitioning for Coreference Resolution. In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 47–57, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Collaborative Partitioning for Coreference Resolution (Uryupina & Moschitti, CoNLL 2017)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/K17-1007.pdf