Addressing Troublesome Words in Neural Machine Translation
One of the weaknesses of Neural Machine Translation (NMT) is in handling lowfrequency and ambiguous words, which we refer as troublesome words. To address this problem, we propose a novel memoryenhanced NMT method. First, we investigate different strategies to define and detect the troublesome words. Then, a contextual memory is constructed to memorize which target words should be produced in what situations. Finally, we design a hybrid model to dynamically access the contextual memory so as to correctly translate the troublesome words. The extensive experiments on Chinese-to-English and English-to-German translation tasks demonstrate that our method significantly outperforms the strong baseline models in translation quality, especially in handling troublesome words.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationNMTTranslationSimilar Papers 제목 키워드 기반
Enhanced Simultaneous Machine Translation with Word-level Policies
Recent years have seen remarkable advances in the field of Simultaneous Machine Translation (SiMT) due to the introduction of innovative policies that dictate whether to READ or WRITE at each step of the translation proc…
Machine TranslationTranslationBLEU Meets COMET: Combining Lexical and Neural Metrics Towards Robust Machine Translation Evaluation
Although neural-based machine translation evaluation metrics, such as COMET or BLEURT, have achieved strong correlations with human judgements, they are sometimes unreliable in detecting certain phenomena that can be con…
Machine TranslationSentenceTranslationContinuous Learning in Neural Machine Translation using Bilingual Dictionaries
While recent advances in deep learning led to significant improvements in machine translation, neural machine translation is often still not able to continuously adapt to the environment. For humans, as well as for machi…
LEMMAMachine TranslationOne-Shot LearningTranslationA Review of Discourse-level Machine Translation
Machine translation (MT) models usually translate a text at sentence level by considering isolated sentences, which is based on a strict assumption that the sentences in a text are independent of one another. However, th…
Machine TranslationNMTSentenceTranslationWhen End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation
Though end-to-end speech-to-text translation has been a great success, we argue that the cascaded speech-to-text translation model still has its place, which is usually criticized for the error propagation between automa…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translationspeech-recognition+4