WeTS: A Benchmark for Translation Suggestion

TL;DR

This paper introduces WeTS, a comprehensive benchmark dataset for translation suggestion, along with novel synthetic data generation methods and a Transformer-based model that achieves state-of-the-art results across multiple language pairs.

Contribution

The paper creates the first publicly available benchmark dataset for translation suggestion and proposes new synthetic data methods and a Transformer model that outperforms previous approaches.

Findings

Achieved SOTA results on four translation directions.

Developed synthetic corpus generation methods.

Provided publicly available benchmark and code.

Abstract

Translation Suggestion (TS), which provides alternatives for specific words or phrases given the entire documents translated by machine translation (MT) \cite{lee2021intellicat}, has been proven to play a significant role in post editing (PE). However, there is still no publicly available data set to support in-depth research for this problem, and no reproducible experimental results can be followed by researchers in this community. To break this limitation, we create a benchmark data set for TS, called \emph{WeTS}, which contains golden corpus annotated by expert translators on four translation directions. Apart from the human-annotated golden corpus, we also propose several novel methods to generate synthetic corpus which can substantially improve the performance of TS. With the corpus we construct, we introduce the Transformer-based model for TS, and experimental results show that our model achieves State-Of-The-Art (SOTA) results on all four translation directions, including English-to-German, German-to-English, Chinese-to-English and English-to-Chinese. Codes and corpus can be found at https://github.com/ZhenYangIACAS/WeTS.git.