Language-Informed Beam Search Decoding for Multilingual Machine Translation

Yilin Yang, Stefan Lee, Prasad Tadepalli
8/11/2024
cs.CL

No official code found. Best implementation: yilinyang7/fairseq_multi_fix (13 stars, MIT, last commit 2024-08-12).

Abstract

Beam search decoding is the de-facto method for decoding auto-regressive Neural Machine Translation (NMT) models, including multilingual NMT where the target language is specified as an input. However, decoding multilingual NMT models commonly produces ``off-target'' translations -- yielding translation outputs not in the intended language. In this paper, we first conduct an error analysis of off-target translations for a strong multilingual NMT model and identify how these decodings are produced during beam search. We then propose Language-informed Beam Search (LiBS), a general decoding algorithm incorporating an off-the-shelf Language Identification (LiD) model into beam search decoding to reduce off-target translations. LiBS is an inference-time procedure that is NMT-model agnostic and does not require any additional parallel data. Results show that our proposed LiBS algorithm on average improves +1.1 BLEU and +0.9 BLEU on WMT and OPUS datasets, and reduces off-target rates from 22.9\% to 7.7\% and 65.8\% to 25.3\% respectively.

View on arXivView PDF

Code Implementations(1)

yilinyang7/fairseq_multi_fixCommunity100%
MIT

Code and Data release for "Improving Multilingual Translation by Representation and Gradient Regularization" (Yang et al. EMNLP 2021), and "Language-Informed Beam Search Decoding for Multilingual Machine Translation" (Yang et al. ACL 2024)

131C++, LuaSep 6, 20212 years agoMIT

Similar Papers

Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models

82% match1 repo92024

Multi-Hypothesis Distillation of Multilingual Neural Translation Models for Low-Resource Languages

82% match2025

On Search Strategies for Document-Level Neural Machine Translation

82% match2023

Understanding and Addressing the Under-Translation Problem from the Perspective of Decoding Objective

82% match2024

Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation

81% match1 repo302025

EBBS: An Ensemble with Bi-Level Beam Search for Zero-Shot Machine Translation

81% match2024

Cite this paper

@article{yang2024languageinformed,
  title  = {Language-Informed Beam Search Decoding for Multilingual Machine Translation},
  author = {Yilin Yang and Stefan Lee and Prasad Tadepalli},
  year   = {2024},
  eprint = {2408.05738},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2408.05738v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2408.05738.svg)](https://codeofpaper.com/paper/2408.05738)

Discussion