Unsupervised Pronoun Resolution via Masked Noun-Phrase Prediction

Ming Shen, Pratyay Banerjee, Chitta Baral


Abstract
In this work, we propose Masked Noun-Phrase Prediction (MNPP), a pre-training strategy to tackle pronoun resolution in a fully unsupervised setting. Firstly, We evaluate our pre-trained model on various pronoun resolution datasets without any finetuning. Our method outperforms all previous unsupervised methods on all datasets by large margins. Secondly, we proceed to a few-shot setting where we finetune our pre-trained model on WinoGrande-S and XS separately. Our method outperforms RoBERTa-large baseline with large margins, meanwhile, achieving a higher AUC score after further finetuning on the remaining three official splits of WinoGrande.
Anthology ID:
2021.acl-short.117
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
932–941
Language:
URL:
https://aclanthology.org/2021.acl-short.117
DOI:
10.18653/v1/2021.acl-short.117
Bibkey:
Cite (ACL):
Ming Shen, Pratyay Banerjee, and Chitta Baral. 2021. Unsupervised Pronoun Resolution via Masked Noun-Phrase Prediction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 932–941, Online. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Pronoun Resolution via Masked Noun-Phrase Prediction (Shen et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-short.117.pdf
Video:
 https://aclanthology.org/2021.acl-short.117.mp4
Data
Definite Pronoun Resolution DatasetGAP Coreference DatasetPG-19WSCWinoGrande