# A Survey on Zero Pronoun Translation

arXiv: https://arxiv.org/abs/2305.10196 · HTML: https://mlsanity.com/paper/2305.10196/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 78 references that are in the map.
- First posted on arXiv 17 May 2023.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [Document-Level Machine Translation with Large Language Models](https://mlsanity.com/paper/2304.02210/) (2023)
- [Has Machine Translation Achieved Human Parity? A Case for Document-level Evaluation](https://mlsanity.com/paper/1808.07048/) (2018)
- [Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models](https://mlsanity.com/paper/2303.13809/) (2023)
- [Document-Level Neural Machine Translation with Hierarchical Attention Networks](https://mlsanity.com/paper/1809.01576/) (2018)
- [A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestion](https://mlsanity.com/paper/1507.02221/) (2015)
- [Improving Multi-turn Dialogue Modelling with Utterance ReWriter](https://mlsanity.com/paper/1906.07004/) (2019)
- [Exploiting Cross-Sentence Context for Neural Machine Translation](https://mlsanity.com/paper/1704.04347/) (2017)
- [Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translation](https://mlsanity.com/paper/1906.12068/) (2019)
- [Context-Aware Monolingual Repair for Neural Machine Translation](https://mlsanity.com/paper/1909.01383/) (2019)
- [Discourse Probing of Pretrained Language Models](https://mlsanity.com/paper/2104.05882/) (2021)
- [Revisiting Round-Trip Translation for Quality Estimation](https://mlsanity.com/paper/2004.13937/) (2020)
- [Evaluation Benchmarks and Learning Criteria for Discourse-Aware Sentence Representations](https://mlsanity.com/paper/1909.00142/) (2019)
- [A Paradigm Shift: The Future of Machine Translation Lies with Large Language Models](https://mlsanity.com/paper/2305.01181/) (2023)
- [TranSmart: A Practical Interactive Machine Translation System](https://mlsanity.com/paper/2105.13072/) (2021)
- [Translating Pro-Drop Languages with Reconstruction Models](https://mlsanity.com/paper/1801.03257/) (2018)
- [One Model to Learn Both: Zero Pronoun Prediction and Translation](https://mlsanity.com/paper/1909.00369/) (2019)
- [Automatic Construction of Discourse Corpora for Dialogue Translation](https://mlsanity.com/paper/1605.06770/) (2016)
- [A Novel Approach to Dropped Pronoun Translation](https://mlsanity.com/paper/1604.06285/) (2016)
- [Contrastive Learning for Context-aware Neural Machine TranslationUsing Coreference Information](https://mlsanity.com/paper/2109.05712/) (2021)
- [Learning to Jointly Translate and Predict Dropped Pronouns with a Shared Reconstruction Mechanism](https://mlsanity.com/paper/1810.06195/) (2018)
- [Pronoun-Targeted Fine-tuning for NMT with Hybrid Losses](https://mlsanity.com/paper/2010.07638/) (2020)
- [Neural Recovery Machine for Chinese Dropped Pronoun](https://mlsanity.com/paper/1605.02134/) (2016)
- [Zero-pronoun Data Augmentation for Japanese-to-English Translation](https://mlsanity.com/paper/2107.00318/) (2021)
- [Controlling Extra-Textual Attributes about Dialogue Participants -- A Case Study of English-to-Polish Neural Machine Translation](https://mlsanity.com/paper/2205.04747/) (2022)
- [Recovering Dropped Pronouns in Chinese Conversations via Modeling Their Referents](https://mlsanity.com/paper/1906.02128/) (2019)

## Built on by (most cited first, 9 of 9)

- [Adapting Large Language Models for Document-Level Machine Translation](https://mlsanity.com/paper/2401.06468/) (2024)
- [Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMs](https://mlsanity.com/paper/2311.03127/) (2023)
- [What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study](https://mlsanity.com/paper/2410.00545/) (2024)
- [Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling](https://mlsanity.com/paper/2307.08074/) (2023)
- [STRUCTSURVEY: Structured Agentic Retrieval for Automated Survey Paper Generation](https://mlsanity.com/paper/2607.01243/) (2026)
- [How Does Pretraining Improve Discourse-Aware Translation?](https://mlsanity.com/paper/2305.19847/) (2023)
- [Current State-of-the-Art of Bias Detection and Mitigation in Machine Translation for African and European Languages: a Review](https://mlsanity.com/paper/2410.21126/) (2024)
- [Beyond the Sentence: A Survey on Context-Aware Machine Translation with Large Language Models](https://mlsanity.com/paper/2506.07583/) (2025)
- [How Much Do LLMs Know About Chinese Zero Pronouns?](https://mlsanity.com/paper/2605.31056/) (2026)

## Abstract (arXiv)

Zero pronouns (ZPs) are frequently omitted in pro-drop languages (e.g. Chinese, Hungarian, and Hindi), but should be recalled in non-pro-drop languages (e.g. English). This phenomenon has been studied extensively in machine translation (MT), as it poses a significant challenge for MT systems due to the difficulty in determining the correct antecedent for the pronoun. This survey paper highlights the major works that have been undertaken in zero pronoun translation (ZPT) after the neural revolution, so that researchers can recognise the current state and future directions of this field. We provide an organisation of the literature based on evolution, dataset, method and evaluation. In addition, we compare and analyze competing models and evaluation metrics on different benchmarks. We uncover a number of insightful findings such as: 1) ZPT is in line with the development trend of large language model; 2) data limitation causes learning bias in languages and domains; 3) performance improvements are often reported on single benchmarks, but advanced methods are still far from real-world use; 4) general-purpose metrics are not reliable on nuances and complexities of ZPT, emphasizing the necessity of targeted metrics; 5) apart from commonly-cited errors, ZPs will cause risks of gender bias.