# Domain Adaptation of Neural Machine Translation by Lexicon Induction

arXiv: https://arxiv.org/abs/1906.00376 · HTML: https://mlsanity.com/paper/1906.00376/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jun 2019.

## Built on by (most cited first, 30 of 33)

- [Word Alignment by Fine-tuning Embeddings on Parallel Corpora](https://mlsanity.com/paper/2101.08231/) (2021)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Adaptive Machine Translation with Large Language Models](https://mlsanity.com/paper/2301.13294/) (2023)
- [Benchmarking Machine Translation with Cultural Awareness](https://mlsanity.com/paper/2305.14328/) (2023)
- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [Machine Translation into Low-resource Language Varieties](https://mlsanity.com/paper/2106.06797/) (2021)
- [Domain Terminology Integration into Machine Translation: Leveraging Large Language Models](https://mlsanity.com/paper/2310.14451/) (2023)
- [Don't Go Far Off: An Empirical Study on Neural Poetry Translation](https://mlsanity.com/paper/2109.02972/) (2021)
- [DEEP: DEnoising Entity Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2111.07393/) (2021)
- [Non-Parametric Domain Adaptation for End-to-End Speech Translation](https://mlsanity.com/paper/2205.11211/) (2022)
- [Simple and Scalable Nearest Neighbor Machine Translation](https://mlsanity.com/paper/2302.12188/) (2023)
- [Improving Both Domain Robustness and Domain Adaptability in Machine Translation](https://mlsanity.com/paper/2112.08288/) (2021)
- [Zero-shot Domain Adaptation for Neural Machine Translation with Retrieved Phrase-level Prompts](https://mlsanity.com/paper/2209.11409/) (2022)
- [What Knowledge Is Needed? Towards Explainable Memory for kNN-MT Domain Adaptation](https://mlsanity.com/paper/2211.04052/) (2022)
- [LLM-based Translation Inference with Iterative Bilingual Understanding](https://mlsanity.com/paper/2410.12543/) (2024)
- [Twist Decoding: Diverse Generators Guide Each Other](https://mlsanity.com/paper/2205.09273/) (2022)
- [Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction](https://mlsanity.com/paper/2105.05498/) (2021)
- [Variance-Aware Machine Translation Test Sets](https://mlsanity.com/paper/2111.04079/) (2021)
- [Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles](https://mlsanity.com/paper/2311.02310/) (2023)
- [LexGen: Domain-aware Multilingual Lexicon Generation](https://mlsanity.com/paper/2405.11200/) (2024)
- [KpopMT: Translation Dataset with Terminology for Kpop Fandom](https://mlsanity.com/paper/2407.07413/) (2024)
- [Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection](https://mlsanity.com/paper/2109.04292/) (2021)
- [Pluggable Neural Machine Translation Models via Memory-augmented Adapters](https://mlsanity.com/paper/2307.06029/) (2023)
- [From Priest to Doctor: Domain Adaptation for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/2412.00966/) (2024)
- [BanglaSTEM: A Parallel Corpus for Technical Domain Bangla-English Translation](https://mlsanity.com/paper/2511.03498/) (2025)
- [Learning How to Translate North Korean through South Korean](https://mlsanity.com/paper/2201.11258/) (2022)
- [Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment](https://mlsanity.com/paper/2205.11616/) (2022)
- [Bridging the Domain Gaps in Context Representations for k-Nearest Neighbor Neural Machine Translation](https://mlsanity.com/paper/2305.16599/) (2023)
- [In-Domain African Languages Translation Using LLMs and Multi-armed Bandits](https://mlsanity.com/paper/2505.15069/) (2025)
- [Efficient Covariance Estimation for Sparsified Functional Data](https://mlsanity.com/paper/2511.18237/) (2025)

## Abstract (arXiv)

It has been previously noted that neural machine translation (NMT) is very sensitive to domain shift. In this paper, we argue that this is a dual effect of the highly lexicalized nature of NMT, resulting in failure for sentences with large numbers of unknown words, and lack of supervision for domain-specific words. To remedy this problem, we propose an unsupervised adaptation method which fine-tunes a pre-trained out-of-domain NMT model using a pseudo-in-domain corpus. Specifically, we perform lexicon induction to extract an in-domain lexicon, and construct a pseudo-parallel in-domain corpus by performing word-for-word back-translation of monolingual in-domain target sentences. In five domains over twenty pairwise adaptation settings and two model architectures, our method achieves consistent improvements without using any in-domain parallel sentences, improving up to 14 BLEU over unadapted models, and up to 2 BLEU over strong back-translation baselines.