On Search Strategies for Document-Level Neural Machine Translation
Compared to sentence-level systems, document-level neural machine translation (NMT) models produce a more consistent output across a document and are able to better resolve ambiguities within the input. There are many works on document-level NMT, mostly focusing on modifying the model architecture or training strategy to better accommodate the additional context-input. On the other hand, in most works, the question on how to perform search with the trained model is scarcely discussed, sometimes not mentioned at all. In this work, we aim to answer the question how to best utilize a context-aware translation model in decoding. We start with the most popular document-level NMT approach and compare different decoding schemes, some from the literature and others proposed by us. In the comparison, we are using both, standard automatic metrics, as well as specific linguistic phenomena on three standard document-level translation benchmarks. We find that most commonly used decoding strategies perform similar to each other and that higher quality context information has the potential to further improve the translation.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationNMTSentenceTranslationSimilar Papers 제목 키워드 기반
A Survey on Document-level Neural Machine Translation: Methods and Evaluation
Machine translation (MT) is an important task in natural language processing (NLP) as it automates the translation process and reduces the reliance on human translators. With the resurgence of neural networks, the transl…
Document Level Machine TranslationMachine TranslationTranslationAdapting Large Language Models for Document-Level Machine Translation
Large language models (LLMs) have significantly advanced various natural language processing (NLP) tasks. Recent research indicates that moderately-sized LLMs often outperform larger ones after task-specific fine-tuning.…
Document Level Machine TranslationDomain GeneralizationMachine TranslationTranslationMicrosoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation
This paper describes the Microsoft Translator submissions to the WMT19 news translation shared task for English-German. Our main focus is document-level neural machine translation with deep transformer models. We start w…
Data AugmentationMachine TranslationSentenceTranslationHas Machine Translation Achieved Human Parity? A Case for Document-level Evaluation
Recent research suggests that neural machine translation achieves parity with professional human translation on the WMT Chinese--English news translation task. We empirically test this claim with alternative evaluation p…
Machine TranslationSentenceTranslationDynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning
Document-level neural machine translation has yielded attractive improvements. However, majority of existing methods roughly use all context sentences in a fixed scope. They neglect the fact that different source sentenc…
Machine Translationreinforcement-learningReinforcement Learning (RL)Sentence+1