# End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages

arXiv: https://arxiv.org/abs/2106.12398 · HTML: https://mlsanity.com/paper/2106.12398/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 23 Jun 2021.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Marian: Fast Neural Machine Translation in C++](https://mlsanity.com/paper/1804.00344/) (2018)
- [Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation](https://mlsanity.com/paper/1804.06609/) (2018)
- [Guided Open Vocabulary Image Captioning with Constrained Beam Search](https://mlsanity.com/paper/1612.00576/) (2016)
- [Training Neural Machine Translation To Apply Terminology Constraints](https://mlsanity.com/paper/1906.01105/) (2019)
- [Code-Switching for Enhancing NMT with Pre-Specified Translation](https://mlsanity.com/paper/1904.09107/) (2019)
- [Addressing the Rare Word Problem in Neural Machine Translation](https://mlsanity.com/paper/1410.8206/) (2014)
- [Neural Machine Translation Decoding with Terminology Constraints](https://mlsanity.com/paper/1805.03750/) (2018)
- [SYSTRAN's Pure Neural Machine Translation Systems](https://mlsanity.com/paper/1610.05540/) (2016)
- [Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model](https://mlsanity.com/paper/2011.11499/) (2020)
- [Facilitating Terminology Translation with Target Lemma Annotations](https://mlsanity.com/paper/2101.10035/) (2021)
- [Announcing CzEng 2.0 Parallel Corpus with over 2 Gigawords](https://mlsanity.com/paper/2007.03006/) (2020)

## Built on by (most cited first, 6 of 6)

- [BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models](https://mlsanity.com/paper/2306.10968/) (2023)
- [CUNI systems for WMT21: Terminology translation Shared Task](https://mlsanity.com/paper/2109.09350/) (2021)
- [Negative Lexical Constraints in Neural Machine Translation](https://mlsanity.com/paper/2308.03601/) (2023)
- [A Template-based Method for Constrained Neural Machine Translation](https://mlsanity.com/paper/2205.11255/) (2022)
- [Open Terminology Management and Sharing Toolkit for Federation of Terminology Databases](https://mlsanity.com/paper/2207.06729/) (2022)
- [Improving Neural Machine Translation by Multi-Knowledge Integration with Prompting](https://mlsanity.com/paper/2312.04807/) (2023)

## Abstract (arXiv)

Lexically constrained machine translation allows the user to manipulate the output sentence by enforcing the presence or absence of certain words and phrases. Although current approaches can enforce terms to appear in the translation, they often struggle to make the constraint word form agree with the rest of the generated output. Our manual analysis shows that 46% of the errors in the output of a baseline constrained model for English to Czech translation are related to agreement. We investigate mechanisms to allow neural machine translation to infer the correct word inflection given lemmatized constraints. In particular, we focus on methods based on training the model with constraints provided as part of the input sequence. Our experiments on the English-Czech language pair show that this approach improves the translation of constrained terms in both automatic and manual evaluation by reducing errors in agreement. Our approach thus eliminates inflection errors, without introducing new errors or decreasing the overall quality of the translation.