# Rethinking Word-Level Auto-Completion in Computer-Aided Translation

arXiv: https://arxiv.org/abs/2310.14523 · HTML: https://mlsanity.com/paper/2310.14523/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 30 references that are in the map.
- First posted on arXiv 23 Oct 2023.

## Builds on (most cited first, 7 of 7)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [TranSmart: A Practical Interactive Machine Translation System](https://mlsanity.com/paper/2105.13072/) (2021)
- [GWLAN: General Word-Level AutocompletioN for Computer-Aided Translation](https://mlsanity.com/paper/2105.14913/) (2021)
- [Correct-and-Memorize: Learning to Translate from Interactive Revisions](https://mlsanity.com/paper/1907.03468/) (2019)
- [Translation Word-Level Auto-Completion: What can we achieve out of the box?](https://mlsanity.com/paper/2210.12802/) (2022)

## Abstract (arXiv)

Word-Level Auto-Completion (WLAC) plays a crucial role in Computer-Assisted Translation. It aims at providing word-level auto-completion suggestions for human translators. While previous studies have primarily focused on designing complex model architectures, this paper takes a different perspective by rethinking the fundamental question: what kind of words are good auto-completions? We introduce a measurable criterion to answer this question and discover that existing WLAC models often fail to meet this criterion. Building upon this observation, we propose an effective approach to enhance WLAC performance by promoting adherence to the criterion. Notably, the proposed approach is general and can be applied to various encoder-based architectures. Through extensive experiments, we demonstrate that our approach outperforms the top-performing system submitted to the WLAC shared tasks in WMT2022, while utilizing significantly smaller model sizes.