# Interactive-Predictive Neural Machine Translation through Reinforcement and Imitation

arXiv: https://arxiv.org/abs/1907.02326 · HTML: https://mlsanity.com/paper/1907.02326/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2019.

## Built on by (most cited first, 7 of 7)

- [Survey on reinforcement learning for language processing](https://mlsanity.com/paper/2104.05565/) (2021)
- [Phrase-level Active Learning for Neural Machine Translation](https://mlsanity.com/paper/2106.11375/) (2021)
- [To Label or Not to Label: Hybrid Active Learning for Neural Machine Translation](https://mlsanity.com/paper/2403.09259/) (2024)
- [Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation Training](https://mlsanity.com/paper/2307.08416/) (2023)
- [Prompting Large Language Models with Human Error Markings for Self-Correcting Machine Translation](https://mlsanity.com/paper/2406.02267/) (2024)
- [Gradient Imitation Reinforcement Learning for General Low-Resource Information Extraction](https://mlsanity.com/paper/2211.06014/) (2022)
- [Policy Learning with a Natural Language Action Space: A Causal Approach](https://mlsanity.com/paper/2502.17538/) (2025)

## Abstract (arXiv)

We propose an interactive-predictive neural machine translation framework for easier model personalization using reinforcement and imitation learning. During the interactive translation process, the user is asked for feedback on uncertain locations identified by the system. Responses are weak feedback in the form of "keep" and "delete" edits, and expert demonstrations in the form of "substitute" edits. Conditioning on the collected feedback, the system creates alternative translations via constrained beam search. In simulation experiments on two language pairs our systems get close to the performance of supervised training with much less human effort.