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
Posted Content
Fine-grained Entity Typing through Increased Discourse Context and Adaptive Classification Thresholds.
TL;DR: This article propose a neural architecture which learns a distributional semantic representation that leverages a greater amount of semantic context (both document and sentence level information) than prior work, and find that additional context improves performance, with further improvements gained by utilizing adaptive classification thresholds.
Proceedings ArticleDOI
Analysis and Prediction of Unalignable Words in Parallel Text
TL;DR: A simple and effective method to improve automatic word alignment by pre-removing unalignable words is proposed, and improvements on hierarchical MT systems in both translation directions are shown.
Journal ArticleDOI
Generalized Hierarchical Word Sequence Framework for Language Modeling
TL;DR: A generalized hierarchical word sequence framework, where different word association scores can be adopted to rearrange word sequences in a totally unsupervised fashion, to be considered as a better alternative for n-gram language models.
Modeling the Interpretation of Discourse Connectives
TL;DR: Evaluation against the sense annotation of the Penn Discourse Treebank confirms the superiority of the model over literal comprehension, and demonstrates that the proposed model improves automatic discourse parsing.
Machine Translation Believability
TL;DR: The authors study the relationship of believability to fluency and adequacy by applying traditional MT direct assessment protocols to annotate all three features on the output of neural MT systems, and they find that it is closely related to but distinct from fluency, and initial qualitative analysis suggests that semantic features may explain the difference.