Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution
This work addresses a specific problem in natural language processing for Japanese language applications, representing an incremental advance.
The authors tackled zero anaphora resolution by proposing a new pretraining task and finetuning method for masked language models, resulting in state-of-the-art performance improvements on Japanese datasets.
Masked language models (MLMs) have contributed to drastic performance improvements with regard to zero anaphora resolution (ZAR). To further improve this approach, in this study, we made two proposals. The first is a new pretraining task that trains MLMs on anaphoric relations with explicit supervision, and the second proposal is a new finetuning method that remedies a notorious issue, the pretrain-finetune discrepancy. Our experiments on Japanese ZAR demonstrated that our two proposals boost the state-of-the-art performance, and our detailed analysis provides new insights on the remaining challenges.