paper-with-me

Papers

Improving Retrieval-Augmented Neural Machine Translation with Monolingual Data

2025-04-30 · Maxime Bouthors, Josep Crego, François Yvon

Conventional retrieval-augmented neural machine translation (RANMT) systems leverage bilingual corpora, e.g., translation memories (TMs). Yet, in many settings, in-domain monolingual target-side corpora are often available. This work explores ways to take advantage of such resources by retrieving relevant segments directly in the target language, based on a source-side query. For this, we design improved cross-lingual retrieval systems, trained with both sentence level and word-level matching objectives. In our experiments with two RANMT architectures, we first demonstrate the benefits of such cross-lingual objectives in a controlled setting, obtaining translation performances that surpass standard TM-based models. We then showcase our method on a real-world set-up, where the target monolingual resources far exceed the amount of parallel data and observe large improvements of our new techniques, which outperform both the baseline setting, and general-purpose cross-lingual retrievers.

📄 PDF Abstract BibTeX arXiv:2504.21747

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationRetrievalSentenceTranslation

Similar Papers 제목 키워드 기반

Neural Machine Translation with Monolingual Translation Memory

2021-05-24 · ACL 2021 5 · Deng Cai, Yan Wang, Huayang Li, Wai Lam 외

Prior work has proved that Translation memory (TM) can boost the performance of Neural Machine Translation (NMT). In contrast to existing work that uses bilingual corpus as TM and employs source-side similarity search fo…

Domain AdaptationMachine TranslationNMTRetrieval+1

An Efficient Approach for Machine Translation on Low-resource Languages: A Case Study in Vietnamese-Chinese

2025-01-31 · Tran Ngoc Son, Nguyen Anh Tu, Nguyen Minh Tri

Despite the rise of recent neural networks in machine translation, those networks do not work well if the training data is insufficient. In this paper, we proposed an approach for machine translation in low-resource lang…

Language ModelingLanguage ModellingMachine TranslationTranslation

DEEP: DEnoising Entity Pre-training for Neural Machine Translation

2022-01-16 · ACL ARR January 2022 1 · Anonymous

It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus. Earlier named entity translation methods mainly focus on phonetic transl…

DenoisingMachine TranslationMulti-Task LearningSentence+2

DEEP: DEnoising Entity Pre-training for Neural Machine Translation

2021-11-14 · ACL 2022 5 · Junjie Hu, Hiroaki Hayashi, Kyunghyun Cho, Graham Neubig

It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus. Earlier named entity translation methods mainly focus on phonetic transl…

DenoisingMachine TranslationMulti-Task LearningSentence+2

Bridging Language Gaps: Advances in Cross-Lingual Information Retrieval with Multilingual LLMs

2025-10-01 · Roksana Goworek, Olivia Macmillan-Scott, Eda B. Özyiğit arxiv

Cross-lingual information retrieval (CLIR) addresses the challenge of retrieving relevant documents written in languages different from that of the original query. Research in this area has typically framed the task as m…

Information RetrievalQuestion AnsweringAnswer Generation