Johns Hopkins University, HLTCOE
Stieff Building / 810 Wyman Park Drive
Baltimore, MD 21211-2840, USA
Email: email@example.com where x=kevinduh
Hi! I am a senior research scientist at the Johns Hopkins University Human Language Technology Center of Excellence (HLTCOE). I am also an assistant research professor in the Department of Computer Science and a member of the Center for Language and Speech Processing (CLSP). Previously, I was assistant professor at the Nara Institute of Science and Technology (2012-2015) and research associate at NTT CS Labs (2009-2012). I received my B.S. in 2003 from Rice University, and PhD in 2009 from the University of Washington, both in Electrical Engineering. My research interests lie at the intersection of Natural Language Processing and Machine Learning, in particular on areas relating to machine translation, semantics, and deep learning.
My recent projects include: (a) representation learning for words and sentences, (b) neural sequence-to-sequence models and their extensions for machine translation, information extraction, and search (c) multi-objective optimization for fast, small, and accurate deep learning models. I'm fortunate to have great collaborators.
Selected Publications [click here for full list, or Google scholar profile]:
- Ordinal Common-sense Inference (TACL2017)
- MT/IE: Cross-lingual Open Information Extraction with Neural Sequence-to-Sequence Models (EACL2017)
- Streaming Word Embeddings with the Space-Saving Algorithm
- Robsut Wrod Reocginiton via Semi-Character Recurrent Neural Network (AAAI2017)
- Automated structure discovery of neural network language model based on evolution strategy (SLT2016)
- Representation Learning using Multi-Task Deep Neural Nets for Semantic Classification & IR (NAACL2015)
- Multilingual Topic Models for Bilingual Dictionary Extraction (ACM TALLIP 2015)
- Learning to Translate with Multiple Objectives (ACL2012)
- Learning to Rank with Partially-Labeled Data (SIGIR2008)
- Program Chair of EMNLP 2016 (with Xavier Carreras); Check out the talk videos.
- SCALE'16 Workshop on Computer Assisted Discovery, Extraction, and Translation (CADET)
To prospective students/interns/postdocs: Thanks for your interest! I am not able to reply to your inquiries individually, due to the large volumes of email I receive ("email event horizon"). If you are seeking admission, please refer to the official admissions page for more information.