mlsanityData to 7 Oct 2026

Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution

arXiv 2104.07425 ↗First posted 15 Apr 2021cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 17 of its 42 references that are in the map. First posted on arXiv 15 Apr 2021.

Builds on

17 of 42 references.

References · 17

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  5. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  6. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  7. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  8. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 668
  9. 2019BERT for Coreference Resolution: Baselines and Analysiscited by 125
  10. 2020Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classificationcited by 98
  11. 2019A Surprisingly Robust Trick for Winograd Schema Challengecited by 30
  12. 2020An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolutioncited by 4
5 more
  1. 2016Generating and Exploiting Large-scale Pseudo Training Data for Zero Pronoun Resolutioncited by 3
  2. 2019Multi-task Learning for Japanese Predicate Argument Structure Analysiscited by 3
  3. 2018Distance-Free Modeling of Multi-Predicate Interactions in End-to-End Japanese Predicate-Argument Structure Analysiscited by 2
  4. 2018Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysiscited by 1
  5. 2019Semantic Role Labeling with Associated Memory Networkcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 0; 2024: 1; 2025: 0; 2026: 1.

4 papers.

  1. 2022Do language models make human-like predictions about the coreferents of Italian anaphoric zero pronouns?cited by 1
  2. 2022Joint Coreference Resolution for Zeros and non-Zeros in Arabiccited by 1
  3. 2024To Drop or Not to Drop? Predicting Argument Ellipsis Judgments: A Case Study in Japanesecited by 0
  4. 2026How Much Do LLMs Know About Chinese Zero Pronouns?cited by 0