# Paying Attention to Multi-Word Expressions in Neural Machine Translation

arXiv: https://arxiv.org/abs/1710.06313 · HTML: https://mlsanity.com/paper/1710.06313/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2017.

## Built on by (most cited first, 5 of 5)

- [Chinese Character Decomposition for Neural MT with Multi-Word Expressions](https://mlsanity.com/paper/2104.04497/) (2021)
- [Automatic Evaluation and Analysis of Idioms in Neural Machine Translation](https://mlsanity.com/paper/2210.04545/) (2022)
- [Learn Your Tokens: Word-Pooled Tokenization for Language Modeling](https://mlsanity.com/paper/2310.11628/) (2023)
- [That was the last straw, we need more: Are Translation Systems Sensitive to Disambiguating Context?](https://mlsanity.com/paper/2310.14610/) (2023)
- [An Empirical Study on Chinese Character Decomposition in Multiword Expression-Aware Neural Machine Translation](https://mlsanity.com/paper/2512.15556/) (2025)

## Abstract (arXiv)

Processing of multi-word expressions (MWEs) is a known problem for any natural language processing task. Even neural machine translation (NMT) struggles to overcome it. This paper presents results of experiments on investigating NMT attention allocation to the MWEs and improving automated translation of sentences that contain MWEs in English->Latvian and English->Czech NMT systems. Two improvement strategies were explored -(1) bilingual pairs of automatically extracted MWE candidates were added to the parallel corpus used to train the NMT system, and (2) full sentences containing the automatically extracted MWE candidates were added to the parallel corpus. Both approaches allowed to increase automated evaluation results. The best result - 0.99 BLEU point increase - has been reached with the first approach, while with the second approach minimal improvements achieved. We also provide open-source software and tools used for MWE extraction and alignment inspection.