# Simultaneous Translation with Flexible Policy via Restricted Imitation Learning

arXiv: https://arxiv.org/abs/1906.01135 · HTML: https://mlsanity.com/paper/1906.01135/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2019.

## Built on by (most cited first, 22 of 22)

- [RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer](https://mlsanity.com/paper/2106.04833/) (2021)
- [Information-Transport-based Policy for Simultaneous Translation](https://mlsanity.com/paper/2210.12357/) (2022)
- [Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy](https://mlsanity.com/paper/2109.05238/) (2021)
- [Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR](https://mlsanity.com/paper/2106.06636/) (2021)
- [Hidden Markov Transformer for Simultaneous Machine Translation](https://mlsanity.com/paper/2303.00257/) (2023)
- [Modeling Dual Read/Write Paths for Simultaneous Machine Translation](https://mlsanity.com/paper/2203.09163/) (2022)
- [Gaussian Multi-head Attention for Simultaneous Machine Translation](https://mlsanity.com/paper/2203.09072/) (2022)
- [Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Framework](https://mlsanity.com/paper/2203.09053/) (2022)
- [The USTC-NELSLIP Systems for Simultaneous Speech Translation Task at IWSLT 2021](https://mlsanity.com/paper/2107.00279/) (2021)
- [Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learning](https://mlsanity.com/paper/2002.04306/) (2020)
- [Simultaneous Speech Translation for Live Subtitling: from Delay to Display](https://mlsanity.com/paper/2107.08807/) (2021)
- [Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff](https://mlsanity.com/paper/2309.11379/) (2023)
- [Simultaneous Multi-Pivot Neural Machine Translation](https://mlsanity.com/paper/2104.07410/) (2021)
- [Anticipation-Free Training for Simultaneous Machine Translation](https://mlsanity.com/paper/2201.12868/) (2022)
- [Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement](https://mlsanity.com/paper/2110.09646/) (2021)
- [LEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translation](https://mlsanity.com/paper/2303.11750/) (2023)
- [Visualization: the missing factor in Simultaneous Speech Translation](https://mlsanity.com/paper/2111.00514/) (2021)
- [NAIST-SIC-Aligned: an Aligned English-Japanese Simultaneous Interpretation Corpus](https://mlsanity.com/paper/2304.11766/) (2023)
- [MeetDot: Videoconferencing with Live Translation Captions](https://mlsanity.com/paper/2109.09577/) (2021)
- [On Combining Expert Demonstrations in Imitation Learning via Optimal Transport](https://mlsanity.com/paper/2307.10810/) (2023)
- [Full-Sentence Models Perform Better in Simultaneous Translation Using the Information Enhanced Decoding Strategy](https://mlsanity.com/paper/2105.01893/) (2021)
- [Data-Driven Adaptive Simultaneous Machine Translation](https://mlsanity.com/paper/2204.12672/) (2022)

## Abstract (arXiv)

Simultaneous translation is widely useful but remains one of the most difficult tasks in NLP. Previous work either uses fixed-latency policies, or train a complicated two-staged model using reinforcement learning. We propose a much simpler single model that adds a `delay' token to the target vocabulary, and design a restricted dynamic oracle to greatly simplify training. Experiments on Chinese<->English simultaneous translation show that our work leads to flexible policies that achieve better BLEU scores and lower latencies compared to both fixed and RL-learned policies.