# Autocorrect in the Process of Translation -- Multi-task Learning Improves Dialogue Machine Translation

arXiv: https://arxiv.org/abs/2103.16189 · HTML: https://mlsanity.com/paper/2103.16189/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 30 Mar 2021.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information](https://mlsanity.com/paper/2010.03142/) (2020)
- [Towards Making the Most of BERT in Neural Machine Translation](https://mlsanity.com/paper/1908.05672/) (2019)
- [Improving Robustness of Machine Translation with Synthetic Noise](https://mlsanity.com/paper/1902.09508/) (2019)
- [Towards Robust Neural Machine Translation](https://mlsanity.com/paper/1805.06130/) (2018)
- [Contextual Neural Model for Translating Bilingual Multi-Speaker Conversations](https://mlsanity.com/paper/1809.00344/) (2018)
- [Translating Pro-Drop Languages with Reconstruction Models](https://mlsanity.com/paper/1801.03257/) (2018)
- [DiaBLa: A Corpus of Bilingual Spontaneous Written Dialogues for Machine Translation](https://mlsanity.com/paper/1905.13354/) (2019)
- [Automatic Construction of Discourse Corpora for Dialogue Translation](https://mlsanity.com/paper/1605.06770/) (2016)
- [Neural Machine Translation of Text from Non-Native Speakers](https://mlsanity.com/paper/1808.06267/) (2018)
- [An Analysis of Source-Side Grammatical Errors in NMT](https://mlsanity.com/paper/1905.10024/) (2019)

## Built on by (most cited first, 8 of 8)

- [Modeling Bilingual Conversational Characteristics for Neural Chat Translation](https://mlsanity.com/paper/2107.11164/) (2021)
- [Towards Making the Most of Dialogue Characteristics for Neural Chat Translation](https://mlsanity.com/paper/2109.00668/) (2021)
- [The Cross-lingual Conversation Summarization Challenge](https://mlsanity.com/paper/2205.00379/) (2022)
- [Scheduled Multi-task Learning for Neural Chat Translation](https://mlsanity.com/paper/2205.03766/) (2022)
- [A Case Study on Context-Aware Neural Machine Translation with Multi-Task Learning](https://mlsanity.com/paper/2407.03076/) (2024)
- [A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translation](https://mlsanity.com/paper/2301.11749/) (2023)
- [Secoco: Self-Correcting Encoding for Neural Machine Translation](https://mlsanity.com/paper/2108.12137/) (2021)
- [An Empirical Study on the Robustness of Massively Multilingual Neural Machine Translation](https://mlsanity.com/paper/2405.07673/) (2024)

## Abstract (arXiv)

Automatic translation of dialogue texts is a much needed demand in many real life scenarios. However, the currently existing neural machine translation delivers unsatisfying results. In this paper, we conduct a deep analysis of a dialogue corpus and summarize three major issues on dialogue translation, including pronoun dropping (droppro), punctuation dropping (droppun), and typos (typo). In response to these challenges, we propose a joint learning method to identify omission and typo, and utilize context to translate dialogue utterances. To properly evaluate the performance, we propose a manually annotated dataset with 1,931 Chinese-English parallel utterances from 300 dialogues as a benchmark testbed for dialogue translation. Our experiments show that the proposed method improves translation quality by 3.2 BLEU over the baselines. It also elevates the recovery rate of omitted pronouns from 26.09% to 47.16%. We will publish the code and dataset publicly at https://github.com/rgwt123/DialogueMT.