Y
Yang Liu
Researcher at Tsinghua University
Publications - 235
Citations - 8556
Yang Liu is an academic researcher from Tsinghua University. The author has contributed to research in topics: Machine translation & Computer science. The author has an hindex of 43, co-authored 213 publications receiving 7024 citations. Previous affiliations of Yang Liu include Huawei & Soochow University (Suzhou).
Papers
More filters
Proceedings ArticleDOI
Modeling Coverage for Neural Machine Translation
TL;DR: This paper propose a coverage vector to keep track of the attention history and feed it to the attention model to adjust future attention, which enables NMT system to consider more about untranslated source words.
Proceedings Article
Topical word embeddings
TL;DR: The experimental results show that the TWE models outperform typical word embedding models including the multi-prototype version on contextual word similarity, and also exceed latent topic models and other representative document models on text classification.
Proceedings ArticleDOI
Minimum Risk Training for Neural Machine Translation
TL;DR: This paper proposed minimum risk training for end-to-end NMT, which is capable of optimizing model parameters directly with respect to evaluation metrics and achieves significant improvements over maximum likelihood estimation on a state-of-the-art NMT system.
Proceedings ArticleDOI
Tree-to-String Alignment Template for Statistical Machine Translation
Yang Liu,Qun Liu,Shouxun Lin +2 more
TL;DR: A novel translation model based on tree-to-string alignment template (TAT) which describes the alignment between a source parse tree and a target string that significantly outperforms Pharaoh, a state-of-the-art decoder for phrase-based models.
Proceedings ArticleDOI
Adversarial Training for Unsupervised Bilingual Lexicon Induction
TL;DR: This work shows that cross-lingual connection can actually be established without any form of supervision, by formulating the problem as a natural adversarial game, and investigating techniques that are crucial to successful training.