mlsanityData to 14 Oct 2026

How Effective is Byte Pair Encoding for Out-Of-Vocabulary Words in Neural Machine Translation?

arXiv 2208.05225 ↗First posted 10 Aug 2022cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Neural Machine Translation (NMT) is an open vocabulary problem. As a result, dealing with the words not occurring during training (a.k.a. out-of-vocabulary (OOV) words) have long been a fundamental challenge for NMT systems. The predominant method to tackle this problem is Byte Pair Encoding (BPE) which splits words, including OOV words, into sub-word segments. BPE has achieved impressive results for a wide range of translation tasks in terms of automatic evaluation metrics. While it is often assumed that by using BPE, NMT systems are capable of handling OOV words, the effectiveness of BPE in translating OOV words has not been explicitly measured. In this paper, we study to what extent BPE is successful in translating OOV words at the word-level. We analyze the translation quality of OOV words based on word type, number of segments, cross-attention weights, and the frequency of segment n-grams in the training data. Our experiments show that while careful BPE settings seem to be fairly useful in translating OOV words across datasets, a considerable percentage of OOV words are translated incorrectly. Furthermore, we highlight the slightly higher effectiveness of BPE in translating OOV words for special cases, such as named-entities and when the languages involved are linguistically close to each other.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 22 of its 36 references that are in the map. First posted on arXiv 10 Aug 2022.

Builds on

22 of 36 references.

References · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  4. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  5. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  6. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,475
  7. 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 639
  8. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 560
  9. 2019BPE-Dropout: Simple and Effective Subword Regularizationcited by 195
  10. 2019Facebook FAIR's WMT19 News Translation Task Submissioncited by 179
  11. 2014On Using Very Large Target Vocabulary for Neural Machine Translationcited by 80
  12. 2019Jointly Learning to Align and Translate with Transformer Modelscited by 75
10 more
  1. 2014Addressing the Rare Word Problem in Neural Machine Translationcited by 50
  2. 2016Pointing the Unknown Wordscited by 43
  3. 2020Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translationcited by 38
  4. 2016Character-based Neural Machine Translationcited by 33
  5. 2020Accurate Word Alignment Induction from Neural Machine Translationcited by 32
  6. 2018Revisiting Character-Based Neural Machine Translation with Capacity and Compressioncited by 28
  7. 2018How Much Does Tokenization Affect Neural Machine Translation?cited by 26
  8. 2020Optimizing Transformer for Low-Resource Neural Machine Translationcited by 24
  9. 2020Morphological Word Segmentation on Agglutinative Languages for Neural Machine Translationcited by 11
  10. 2019Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoringcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 1.

3 papers.

  1. 2023Revolutionizing Cyber Threat Detection with Large Language Models: A privacy-preserving BERT-based Lightweight Model for IoT/IIoT Devicescited by 39
  2. 2025Generating particle physics Lagrangians with transformerscited by 1
  3. 2022Impact of Domain-Adapted Multilingual Neural Machine Translation in the Medical Domaincited by 0