# Incorporating Discrete Translation Lexicons into Neural Machine Translation

arXiv: https://arxiv.org/abs/1606.02006 · HTML: https://mlsanity.com/paper/1606.02006/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2016.

## 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)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation](https://mlsanity.com/paper/2302.07856/) (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)
- [Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation](https://mlsanity.com/paper/2106.00903/) (2021)
- [Lexicon Learning for Few-Shot Neural Sequence Modeling](https://mlsanity.com/paper/2106.03993/) (2021)
- [Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT](https://mlsanity.com/paper/2109.01396/) (2021)
- [Chain-of-Dictionary Prompting Elicits Translation in Large Language Models](https://mlsanity.com/paper/2305.06575/) (2023)
- [On the Evaluation of Machine Translation for Terminology Consistency](https://mlsanity.com/paper/2106.11891/) (2021)
- [Don't Go Far Off: An Empirical Study on Neural Poetry Translation](https://mlsanity.com/paper/2109.02972/) (2021)
- [What is the Best Way for ChatGPT to Translate Poetry?](https://mlsanity.com/paper/2406.03450/) (2024)
- [Phrase-level Active Learning for Neural Machine Translation](https://mlsanity.com/paper/2106.11375/) (2021)
- [Lexically Aware Semi-Supervised Learning for OCR Post-Correction](https://mlsanity.com/paper/2111.02622/) (2021)
- [Continuous Learning in Neural Machine Translation using Bilingual Dictionaries](https://mlsanity.com/paper/2102.06558/) (2021)
- [Frequency-Aware Contrastive Learning for Neural Machine Translation](https://mlsanity.com/paper/2112.14484/) (2021)
- [GenAudit: Fixing Factual Errors in Language Model Outputs with Evidence](https://mlsanity.com/paper/2402.12566/) (2024)
- [LLM-based Translation Inference with Iterative Bilingual Understanding](https://mlsanity.com/paper/2410.12543/) (2024)
- [Retrieval-Augmented Code Review Comment Generation](https://mlsanity.com/paper/2506.11591/) (2025)
- [Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages](https://mlsanity.com/paper/2112.08789/) (2021)
- [Improving Retrieval-Augmented Code Comment Generation by Retrieving for Generation](https://mlsanity.com/paper/2408.03623/) (2024)
- [Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models](https://mlsanity.com/paper/2411.01141/) (2024)
- [Word Alignment in the Era of Deep Learning: A Tutorial](https://mlsanity.com/paper/2212.00138/) (2022)
- [Domain Adaptation in Neural Machine Translation using a Qualia-Enriched FrameNet](https://mlsanity.com/paper/2202.10287/) (2022)
- [Cross-Align: Modeling Deep Cross-lingual Interactions for Word Alignment](https://mlsanity.com/paper/2210.04141/) (2022)
- [Extract and Attend: Improving Entity Translation in Neural Machine Translation](https://mlsanity.com/paper/2306.02242/) (2023)
- [Layer-wise Representation Fusion for Compositional Generalization](https://mlsanity.com/paper/2307.10799/) (2023)
- [A Morphologically-Aware Dictionary-based Data Augmentation Technique for Machine Translation of Under-Represented Languages](https://mlsanity.com/paper/2402.01939/) (2024)
- [Bilingual Terminology Extraction from Comparable E-Commerce Corpora](https://mlsanity.com/paper/2104.07398/) (2021)
- [Third-Party Aligner for Neural Word Alignments](https://mlsanity.com/paper/2211.04198/) (2022)

## Abstract (arXiv)

Neural machine translation (NMT) often makes mistakes in translating low-frequency content words that are essential to understanding the meaning of the sentence. We propose a method to alleviate this problem by augmenting NMT systems with discrete translation lexicons that efficiently encode translations of these low-frequency words. We describe a method to calculate the lexicon probability of the next word in the translation candidate by using the attention vector of the NMT model to select which source word lexical probabilities the model should focus on. We test two methods to combine this probability with the standard NMT probability: (1) using it as a bias, and (2) linear interpolation. Experiments on two corpora show an improvement of 2.0-2.3 BLEU and 0.13-0.44 NIST score, and faster convergence time.