Abstract
This paper presents the 3rd-place-winning solution to the GAP coreference resolution shared task. The approach adopted consists of two key components: fine-tuning the BERT language representation model (Devlin et al., 2018) and the usage of external datasets during the training process. The model uses hidden states from the intermediate BERT layers instead of the last layer. The resulting system almost eliminates the difference in log loss per gender during the cross-validation, while providing high performance.- Anthology ID:
- W19-3816
- Volume:
- Proceedings of the First Workshop on Gender Bias in Natural Language Processing
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Marta R. Costa-jussà, Christian Hardmeier, Will Radford, Kellie Webster
- Venue:
- GeBNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 107–112
- Language:
- URL:
- https://aclanthology.org/W19-3816
- DOI:
- 10.18653/v1/W19-3816
- Cite (ACL):
- Artem Abzaliev. 2019. On GAP Coreference Resolution Shared Task: Insights from the 3rd Place Solution. In Proceedings of the First Workshop on Gender Bias in Natural Language Processing, pages 107–112, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- On GAP Coreference Resolution Shared Task: Insights from the 3rd Place Solution (Abzaliev, GeBNLP 2019)
- PDF:
- https://preview.aclanthology.org/fix-volume-bibkeys/W19-3816.pdf
- Data
- GAP Coreference Dataset, WinoBias