K
Kevin Duh
Researcher at Johns Hopkins University
Publications - 205
Citations - 6391
Kevin Duh is an academic researcher from Johns Hopkins University. The author has contributed to research in topics: Machine translation & Parsing. The author has an hindex of 38, co-authored 205 publications receiving 5369 citations. Previous affiliations of Kevin Duh include University of Washington & Nara Institute of Science and Technology.
Papers
More filters
Proceedings ArticleDOI
Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval
TL;DR: This work develops a multi-task DNN for learning representations across multiple tasks, not only leveraging large amounts of cross-task data, but also benefiting from a regularization effect that leads to more general representations to help tasks in new domains.
Posted Content
DyNet: The Dynamic Neural Network Toolkit
Graham Neubig,Chris Dyer,Yoav Goldberg,Austin Matthews,Waleed Ammar,Antonios Anastasopoulos,Miguel Ballesteros,David Chiang,Daniel Clothiaux,Trevor Cohn,Kevin Duh,Manaal Faruqui,Cynthia Gan,Dan Garrette,Yangfeng Ji,Lingpeng Kong,Adhiguna Kuncoro,Gaurav Kumar,Chaitanya Malaviya,Paul Michel,Yusuke Oda,Matthew Richardson,Naomi Saphra,Swabha Swayamdipta,Pengcheng Yin +24 more
TL;DR: DyNet is a toolkit for implementing neural network models based on dynamic declaration of network structure that has an optimized C++ backend and lightweight graph representation and is designed to allow users to implement their models in a way that is idiomatic in their preferred programming language.
Proceedings Article
Automatic Evaluation of Translation Quality for Distant Language Pairs
TL;DR: An automatic evaluation metric based on rank correlation coefficients modified with precision is proposed and meta-evaluation of the NTCIR-7 PATMT JE task data shows that this metric outperforms conventional metrics.
Posted Content
ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension.
TL;DR: This work presents a large-scale dataset, ReCoRD, for machine reading comprehension requiring commonsense reasoning, and demonstrates that the performance of state-of-the-art MRC systems fall far behind human performance.
Proceedings ArticleDOI
Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning
TL;DR: The authors explore weight pruning for BERT and find that low levels of pruning (30-40%) do not affect pre-training loss or transfer to downstream tasks at all.