paper-with-me

홈 › Papers

Learning Kernel-Smoothed Machine Translation with Retrieved Examples

2021-09-21 · EMNLP 2021 11 · Qingnan Jiang, Mingxuan Wang, Jun Cao, Shanbo Cheng, ShuJian Huang, Lei LI

How to effectively adapt neural machine translation (NMT) models according to emerging cases without retraining? Despite the great success of neural machine translation, updating the deployed models online remains a challenge. Existing non-parametric approaches that retrieve similar examples from a database to guide the translation process are promising but are prone to overfit the retrieved examples. In this work, we propose to learn Kernel-Smoothed Translation with Example Retrieval (KSTER), an effective approach to adapt neural machine translation models online. Experiments on domain adaptation and multi-domain machine translation datasets show that even without expensive retraining, KSTER is able to achieve improvement of 1.1 to 1.5 BLEU scores over the best existing online adaptation methods. The code and trained models are released at https://github.com/jiangqn/KSTER.

📄 PDF Abstract BibTeX arXiv:2109.09991

Code (2)

jiangqn/kster 공식 구현 pytorch
cordercorder/knn-models pytorch

Tasks

Domain AdaptationMachine TranslationNMTRetrievalTranslation

Similar Papers 제목 키워드 기반

Guiding Neural Machine Translation with Retrieved Translation Pieces

2018-04-07 · NAACL 2018 6 · Jingyi Zhang, Masao Utiyama, Eiichro Sumita, Graham Neubig 외

One of the difficulties of neural machine translation (NMT) is the recall and appropriate translation of low-frequency words or phrases. In this paper, we propose a simple, fast, and effective method for recalling previo…

Machine TranslationNMTRetrievalSentence+1

An Empirical Study of Many-Shot In-Context Learning for Machine Translation of Low-Resource Languages

2026-04-03 · Yinhan Lu, Gaganpreet Jhajj, Chen Zhang, Anietie Andy 외 arxiv

In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks from a few examples, making it promising for languages underrepresented in pre-training. Recent work on many-shot ICL suggests that mode…

Machine Translation

Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison

2024-04-03 · Maxime Bouthors, Josep Crego, Francois Yvon

Retrieval-Augmented Neural Machine Translation (RAMT) architectures retrieve examples from memory to guide the generation process. While most works in this trend explore new ways to exploit the retrieved examples, the up…

DiversityIn-Context LearningLanguage ModelingLanguage Modelling+4

Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approach

2024-09-13 · Siqi Li, Danni Liu, Jan Niehues

Direct speech translation (ST) models often struggle with rare words. Incorrect translation of these words can have severe consequences, impacting translation quality and user trust. While rare word translation is inhere…

In-Context LearningRetrievalSparse LearningSpeech-to-Text+2

Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions

2018-09-04 · EMNLP 2018 10 · Sho Yokoi, Sosuke Kobayashi, Kenji Fukumizu, Jun Suzuki 외

In this paper, we propose a new kernel-based co-occurrence measure that can be applied to sparse linguistic expressions (e.g., sentences) with a very short learning time, as an alternative to pointwise mutual information…

Machine TranslationSentenceSentence EmbeddingsTranslation