Joint Anaphoricity Detection and Coreference Resolution with Constrained Latent Structures
Abstract
This paper introduces a new structured model for learning anaphoricity detection and coreference resolution in a joint fashion. Specifically,we use a latent tree to represent the full coreference and anaphoric structure of a document at a global level, and we jointly learn the parameters of the two models using a version of the structured perceptron algorithm. Our joint structured model is further refined by the use of pairwise constraints which help the model to capture accurately certain patterns of coreference. Our experiments on the CoNLL-2012 English datasets show large improvements in both coreference resolution and anaphoricity detection, compared to various competing architectures. Our best coreference system obtains a CoNLL score of 81.97 on gold mentions, which is to date the best score reported on this setting.
Cite
Text
Lassalle and Denis. "Joint Anaphoricity Detection and Coreference Resolution with Constrained Latent Structures." AAAI Conference on Artificial Intelligence, 2015. doi:10.1609/AAAI.V29I1.9510Markdown
[Lassalle and Denis. "Joint Anaphoricity Detection and Coreference Resolution with Constrained Latent Structures." AAAI Conference on Artificial Intelligence, 2015.](https://mlanthology.org/aaai/2015/lassalle2015aaai-joint/) doi:10.1609/AAAI.V29I1.9510BibTeX
@inproceedings{lassalle2015aaai-joint,
title = {{Joint Anaphoricity Detection and Coreference Resolution with Constrained Latent Structures}},
author = {Lassalle, Emmanuel and Denis, Pascal},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2015},
pages = {2274-2280},
doi = {10.1609/AAAI.V29I1.9510},
url = {https://mlanthology.org/aaai/2015/lassalle2015aaai-joint/}
}