Improving Retrieval-Augmented Neural Machine Translation with Monolingual Data
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationRetrievalSentenceTranslationSimilar Papers 제목 키워드 기반
Neural Machine Translation with Monolingual Translation Memory
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+1An Efficient Approach for Machine Translation on Low-resource Languages: A Case Study in Vietnamese-Chinese
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 TranslationTranslationDEEP: DEnoising Entity Pre-training for Neural Machine Translation
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+2DEEP: DEnoising Entity Pre-training for Neural Machine Translation
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+2Bridging Language Gaps: Advances in Cross-Lingual Information Retrieval with Multilingual LLMs
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