On the Word Alignment from Neural Machine Translation
Prior researches suggest that neural machine translation (NMT) captures word alignment through its attention mechanism, however, this paper finds attention may almost fail to capture word alignment for some NMT models. This paper thereby proposes two methods to induce word alignment which are general and agnostic to specific NMT models. Experiments show that both methods induce much better word alignment than attention. This paper further visualizes the translation through the word alignment induced by NMT. In particular, it analyzes the effect of alignment errors on translation errors at word level and its quantitative analysis over many testing examples consistently demonstrate that alignment errors are likely to lead to translation errors measured by different metrics.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationNMTTranslationWord AlignmentSimilar Papers 제목 키워드 기반
On the Relationship between Neural Machine Translation and Word Alignment
Prior researches suggest that attentional neural machine translation (NMT) is able to capture word alignment by attention, however, to our surprise, it almost fails for NMT models with multiple attentional layers except …
Machine TranslationNMTTranslationWord AlignmentWord-Alignment-Based Segment-Level Machine Translation Evaluation using Word Embeddings
One of the most important problems in machine translation (MT) evaluation is to evaluate the similarity between translation hypotheses with different surface forms from the reference, especially at the segment level. We …
Machine TranslationTranslationWord AlignmentWord EmbeddingsTarget Foresight Based Attention for Neural Machine Translation
In neural machine translation, an attention model is used to identify the aligned source words for a target word (target foresight word) in order to select translation context, but it does not make use of any information…
Language ModelingLanguage ModellingMachine TranslationTranslationEnd-to-End Neural Word Alignment Outperforms GIZA++
Word alignment was once a core unsupervised learning task in natural language processing because of its essential role in training statistical machine translation (MT) models. Although unnecessary for training neural MT …
Machine TranslationTranslationWord AlignmentOptimizing Word Alignments with Better Subword Tokenization
Word alignment identify translational correspondences between words in a parallel sentence pair and are used and for example and to train statistical machine translation and learn bilingual dictionaries or to perform qua…
Machine TranslationSentenceTranslationWord Alignment