# A Novel Approach to Dropped Pronoun Translation

arXiv: https://arxiv.org/abs/1604.06285 · HTML: https://mlsanity.com/paper/1604.06285/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2016.

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

- [Document-Level Machine Translation with Large Language Models](https://mlsanity.com/paper/2304.02210/) (2023)
- [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)
- [TranSmart: A Practical Interactive Machine Translation System](https://mlsanity.com/paper/2105.13072/) (2021)
- [Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling](https://mlsanity.com/paper/2307.08074/) (2023)
- [A Survey on Zero Pronoun Translation](https://mlsanity.com/paper/2305.10196/) (2023)
- [Zero-pronoun Data Augmentation for Japanese-to-English Translation](https://mlsanity.com/paper/2107.00318/) (2021)
- [A Joint Model for Dropped Pronoun Recovery and Conversational Discourse Parsing in Chinese Conversational Speech](https://mlsanity.com/paper/2106.03345/) (2021)
- [How Does Pretraining Improve Discourse-Aware Translation?](https://mlsanity.com/paper/2305.19847/) (2023)
- [Computational Modelling of Plurality and Definiteness in Chinese Noun Phrases](https://mlsanity.com/paper/2403.04376/) (2024)

## Abstract (arXiv)

Dropped Pronouns (DP) in which pronouns are frequently dropped in the source language but should be retained in the target language are challenge in machine translation. In response to this problem, we propose a semi-supervised approach to recall possibly missing pronouns in the translation. Firstly, we build training data for DP generation in which the DPs are automatically labelled according to the alignment information from a parallel corpus. Secondly, we build a deep learning-based DP generator for input sentences in decoding when no corresponding references exist. More specifically, the generation is two-phase: (1) DP position detection, which is modeled as a sequential labelling task with recurrent neural networks; and (2) DP prediction, which employs a multilayer perceptron with rich features. Finally, we integrate the above outputs into our translation system to recall missing pronouns by both extracting rules from the DP-labelled training data and translating the DP-generated input sentences. Experimental results show that our approach achieves a significant improvement of 1.58 BLEU points in translation performance with 66% F-score for DP generation accuracy.