paper-with-me

홈 › Papers

Refining Source Representations with Relation Networks for Neural Machine Translation

2017-09-12 · Wen Zhang, Jiawei Hu, Yang Feng, Qun Liu

Although neural machine translation (NMT) with the encoder-decoder framework has achieved great success in recent times, it still suffers from some drawbacks: RNNs tend to forget old information which is often useful and the encoder only operates through words without considering word relationship. To solve these problems, we introduce a relation networks (RN) into NMT to refine the encoding representations of the source. In our method, the RN first augments the representation of each source word with its neighbors and reasons all the possible pairwise relations between them. Then the source representations and all the relations are fed to the attention module and the decoder together, keeping the main encoder-decoder architecture unchanged. Experiments on two Chinese-to-English data sets in different scales both show that our method can outperform the competitive baselines significantly.

📄 PDF Abstract BibTeX arXiv:1709.03980

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderMachine TranslationNMTRelationTranslation

Similar Papers 제목 키워드 기반

Refining Source Representations with Relation Networks for Neural Machine Translation

2018-05-25 · COLING 2018 8 · Wen Zhang, Jiawei Hu, Yang Feng, Qun Liu

Although neural machine translation with the encoder-decoder framework has achieved great success recently, it still suffers drawbacks of forgetting distant information, which is an inherent disadvantage of recurrent neu…

DecoderMachine TranslationMemorizationRelation+1

Learning to Refine Source Representations for Neural Machine Translation

2018-12-26 · Xinwei Geng, Long-Yue Wang, Xing Wang, Bing Qin 외

Neural machine translation (NMT) models generally adopt an encoder-decoder architecture for modeling the entire translation process. The encoder summarizes the representation of input sentence from scratch, which is pote…

DecoderMachine TranslationNMTReinforcement Learning+2

Neural Machine Translation with Joint Representation

2020-02-16 · Yanyang Li, Qiang Wang, Tong Xiao, Tongran Liu 외

Though early successes of Statistical Machine Translation (SMT) systems are attributed in part to the explicit modelling of the interaction between any two source and target units, e.g., alignment, the recent Neural Mach…

DecoderMachine TranslationNMTTranslation

Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representations

2020-04-30 · EMNLP 2020 11 · Arturo Oncevay, Barry Haddow, Alexandra Birch

Sparse language vectors from linguistic typology databases and learned embeddings from tasks like multilingual machine translation have been investigated in isolation, without analysing how they could benefit from each o…

ClusteringMachine TranslationTranslation

Learning Source Phrase Representations for Neural Machine Translation

2020-06-25 · ACL 2020 6 · Hongfei Xu, Josef van Genabith, Deyi Xiong, Qiuhui Liu 외

The Transformer translation model (Vaswani et al., 2017) based on a multi-head attention mechanism can be computed effectively in parallel and has significantly pushed forward the performance of Neural Machine Translatio…

Machine TranslationNMTTranslation