Optimizing Differentiable Relaxations of Coreference Evaluation Metrics

Phong Le, Ivan Titov


Abstract
Coreference evaluation metrics are hard to optimize directly as they are non-differentiable functions, not easily decomposable into elementary decisions. Consequently, most approaches optimize objectives only indirectly related to the end goal, resulting in suboptimal performance. Instead, we propose a differentiable relaxation that lends itself to gradient-based optimisation, thus bypassing the need for reinforcement learning or heuristic modification of cross-entropy. We show that by modifying the training objective of a competitive neural coreference system, we obtain a substantial gain in performance. This suggests that our approach can be regarded as a viable alternative to using reinforcement learning or more computationally expensive imitation learning.
Anthology ID:
K17-1039
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:
390–399
Language:
URL:
https://aclanthology.org/K17-1039
DOI:
10.18653/v1/K17-1039
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/K17-1039.pdf
Code
 lephong/diffmetric_coref
Data
CoNLL-2012