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
- 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
- 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)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2021.acl-short.117.pdf
- Data
- Definite Pronoun Resolution Dataset, GAP Coreference Dataset, PG-19, SuperGLUE, WSC, WinoGrande