Q
Qin Gao
Researcher at Carnegie Mellon University
Publications - 23
Citations - 6451
Qin Gao is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Machine translation & Phrase. The author has an hindex of 13, co-authored 23 publications receiving 5403 citations. Previous affiliations of Qin Gao include Microsoft.
Papers
More filters
Posted Content
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Yonghui Wu,Mike Schuster,Zhifeng Chen,Quoc V. Le,Mohammad Norouzi,Wolfgang Macherey,Maxim Krikun,Yuan Cao,Qin Gao,Klaus Macherey,Jeff Klingner,Apurva Shah,Melvin Johnson,Xiaobing Liu,Łukasz Kaiser,Stephan Gouws,Yoshikiyo Kato,Taku Kudo,Hideto Kazawa,Keith Stevens,George Kurian,Nishant Patil,Wei Wang,Cliff Young,Jason A. Smith,Jason Riesa,Alex Rudnick,Oriol Vinyals,Greg S. Corrado,Macduff Hughes,Jeffrey Dean +30 more
TL;DR: GNMT, Google's Neural Machine Translation system, is presented, which attempts to address many of the weaknesses of conventional phrase-based translation systems and provides a good balance between the flexibility of "character"-delimited models and the efficiency of "word"-delicited models.
Proceedings ArticleDOI
Parallel Implementations of Word Alignment Tool
Qin Gao,Stephan Vogel +1 more
TL;DR: Two parallel implementations of GIZA++ that accelerate this word alignment process by showing a near-linear speed-up according to the number of CPUs used, and alignment quality is preserved.
Proceedings Article
Corpus Expansion for Statistical Machine Translation with Semantic Role Label Substitution Rules
Qin Gao,Stephan Vogel +1 more
TL;DR: An approach of expanding parallel corpora for machine translation by utilizing Semantic role labeling on one side of the language pair to extract SRL substitution rules from existing parallel corpus is presented.
Proceedings Article
Consensus versus expertise: a case study of word alignment with Mechanical Turk
Qin Gao,Stephan Vogel +1 more
TL;DR: Experimental results show high precision of the alignments provided by Turkers and the semi-supervised approach achieved 0.5% absolute reduction on alignment error rate, and an easy-to-use interface is developed to simplify the labeling process.
Proceedings Article
A Semi-Supervised Word Alignment Algorithm with Partial Manual Alignments
TL;DR: A word alignment framework that can incorporate partial manual alignments is presented that is a novel semi-supervised algorithm extending the widely used IBM Models with a constrained EM algorithm.