Effective Approaches to Attention-based Neural Machine Translation

Code

• github.com/amitz25/PCCoder
  pytorch★ 49
• github.com/bplank/teaching-dl4nlp
  none★ 4
• github.com/jmyrberg/finnlem
  tf★ 0
• github.com/sooftware/attentions
  pytorch★ 0
• github.com/fqyshelly/CS224n-Winter2019-assignment-solutions
  pytorch★ 0
• github.com/neqkir/attention-mechanism
  tf★ 0
• github.com/hnt4499/seq2seq
  pytorch★ 0
• github.com/varun-bhaseen/Image-caption-generation-using-attention-model
  tf★ 0
• github.com/philipperemy/keras-attention-mechanism
  tf★ 0
• github.com/huulinhcvp/chatBot
  pytorch★ 0

Abstract

An attentional mechanism has lately been used to improve neural machine translation (NMT) by selectively focusing on parts of the source sentence during translation. However, there has been little work exploring useful architectures for attention-based NMT. This paper examines two simple and effective classes of attentional mechanism: a global approach which always attends to all source words and a local one that only looks at a subset of source words at a time. We demonstrate the effectiveness of both approaches over the WMT translation tasks between English and German in both directions. With local attention, we achieve a significant gain of 5.0 BLEU points over non-attentional systems which already incorporate known techniques such as dropout. Our ensemble model using different attention architectures has established a new state-of-the-art result in the WMT'15 English to German translation task with 25.9 BLEU points, an improvement of 1.0 BLEU points over the existing best system backed by NMT and an n-gram reranker.

Tasks

Benchmark Results

Reproductions