paper-with-me

홈 › Papers

Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution

2021-04-15 · EMNLP 2021 11 · Ryuto Konno, Shun Kiyono, Yuichiroh Matsubayashi, Hiroki Ouchi, Kentaro Inui

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.

📄 PDF Abstract BibTeX arXiv:2104.07425

Code (1)

ryuto10/pzero-improves-zar 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Generating and Exploiting Large-scale Pseudo Training Data for Zero Pronoun Resolution

2016-06-06 · ACL 2017 7 · Ting Liu, Yiming Cui, Qingyu Yin, Wei-Nan Zhang 외

Most existing approaches for zero pronoun resolution are heavily relying on annotated data, which is often released by shared task organizers. Therefore, the lack of annotated data becomes a major obstacle in the progres…

Reading Comprehension

Semantic-aware Chinese Zero Pronoun Resolution with Pre-trained Semantic Dependency Parser

2020-10-01 · CCL 2020 10 · Lanqiu Zhang, Zizhuo Shen, Yanqiu Shao

Deep learning-based Chinese zero pronoun resolution model has achieved better performance than traditional machine learning-based model. However, the existing work related to Chinese zero pronoun resolution has not yet w…

Chinese Zero Pronoun ResolutionDeep Learning

Zero Pronoun Resolution with Attention-based Neural Network

2018-08-01 · COLING 2018 8 · Qingyu Yin, Yu Zhang, Wei-Nan Zhang, Ting Liu 외

Recent neural network methods for zero pronoun resolution explore multiple models for generating representation vectors for zero pronouns and their candidate antecedents. Typically, contextual information is utilized to …

Chinese Zero Pronoun Resolution

Tackling Zero Pronoun Resolution and Non-Zero Coreference Resolution Jointly

2021-11-01 · CoNLL (EMNLP) 2021 11 · Shisong Chen, Binbin Gu, Jianfeng Qu, Zhixu Li 외

Zero pronoun resolution aims at recognizing dropped pronouns and pointing out their anaphoric mentions, while non-zero coreference resolution targets at clustering mentions referring to the same entity. Existing efforts …

coreference-resolutionCoreference Resolution

ZPR2: Joint Zero Pronoun Recovery and Resolution using Multi-Task Learning and BERT

2020-07-01 · ACL 2020 6 · Linfeng Song, Kun Xu, Yue Zhang, Jianshu Chen 외

Zero pronoun recovery and resolution aim at recovering the dropped pronoun and pointing out its anaphoric mentions, respectively. We propose to better explore their interaction by solving both tasks together, while the p…

Multi-Task Learning