paper-with-me

홈 › Papers

On the Word Alignment from Neural Machine Translation

2019-07-01 · ACL 2019 7 · Xintong Li, Guanlin Li, Lemao Liu, Max Meng, Shuming Shi

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTTranslationWord Alignment

Similar Papers 제목 키워드 기반

On the Relationship between Neural Machine Translation and Word Alignment

· Xintong Li, Lemao Liu, Guanlin Li, Max Meng 외

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 Alignment

Word-Alignment-Based Segment-Level Machine Translation Evaluation using Word Embeddings

2017-04-02 · Junki Matsuo, Mamoru Komachi, Katsuhito Sudoh

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 Embeddings

Target Foresight Based Attention for Neural Machine Translation

2018-06-01 · NAACL 2018 6 · Xintong Li, Lemao Liu, Zhaopeng Tu, Shuming Shi 외

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 TranslationTranslation

End-to-End Neural Word Alignment Outperforms GIZA++

2020-04-30 · ACL 2020 6 · Thomas Zenkel, Joern Wuebker, John DeNero

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 Alignment

Optimizing Word Alignments with Better Subword Tokenization

2021-08-01 · MTSummit 2021 8 · Anh Khoa Ngo Ho, François Yvon

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