| PHILIP ARTHUR | D, 中間発表 | 知能コミュニケーション | 中村 哲, 松本 裕治, 須藤 克仁, GRAHAM NEUBIG |
|
title: Incorporating Discrete Lexical Translation into Neural Machine Translation
abstract: Neural machine translation (NMT) often makes mistakes in translating low-frequency content words that are essential to understanding the meaning of the sentence. We propose a method to alleviate this problem by augmenting NMT systems with discrete translation lexicons that efficiently encode translations of these low-frequency words. We describe a method to calculate the lexicon probability of the next word in the translation candidate by using the attention vector of the NMT model to select which source word lexical probabilities the model should focus on. We test two methods to combine this probability with the standard NMT probability: (1) using it as a bias, and (2) linear interpolation. Experiments on two corpora show an improvement of 2.0-2.3 BLEU and 0.13-0.44 NIST score, and faster convergence time. language of the presentation: English | |||