David Chiang 蔣偉
Associate Professor, Computer Science and Engineering
Natural Language Processing Group
My research is in natural language processing, the subfield of computer science that aims to enable computers to understand and produce human language. I focus mainly on language translation, and am interested in syntactic parsing and other areas as well.
Teaching
- Fall 2017: CSE 40/60657, Natural Language Processing.
- Spring 2017: CSE 30151, Theory of Computing.
- Fall 2016: CSE 40/60657, Natural Language Processing.
- Spring 2016: CSE 30151, Theory of Computing.
- Fall 2015: CSE 30331, Data Structures.
- Spring 2015: CSE 40/60657, Natural Language Processing.
Recent publications
An unsupervised probability model for speech-to-translation alignment of low-resource Languages. Antonios Anastasopoulos, Long Duong, and David Chiang, 2016. In Proc. EMNLP. PDF
Growing graphs from hyperedge replacement graph grammars. Salvador Aguinaga, Rodrigo Palacios, David Chiang, and Tim Weninger, 2016. In Proc. CIKM. PDF
An attentional model for speech translation without transcription. Long Duong, Antonios Anasatasopoulos, Trevor Cohn, Steven Bird, and David Chiang, 2016. In Proc. NAACL HLT. PDF
Auto-sizing neural networks: with applications to n-gram language models. Kenton Murray and David Chiang, 2015. In Proc. EMNLP. PDF
Supervised phrase table triangulation with neural word embeddings for low-resource languages. Tomer Levinboim and David Chiang, 2015. In Proc. EMNLP.
Model Invertibility Regularization: Sequence alignment with or without parallel data. Tomer Levinboim, Ashish Vaswani and David Chiang, 2015. In Proc. NAACL HLT, pages 609–618. PDF
Multi-task word alignment triangulation for low-resource languages. Tomer Levinboim and David Chiang, 2015. In Proc. NAACL HLT, pages 1221–1226. PDF
Improving word alignment using word similarity. Theerawat Songyot and David Chiang, 2014. In Proc. EMNLP. PDF
Kneser-Ney smoothing on expected counts. Hui Zhang and David Chiang, 2014. In Proc. ACL, 765–774. PDF
Decoding with large-scale neural language models improves
translation. Ashish Vaswani, Yinggong Zhao, Victoria Fossum, and David
Chiang, 2013. In Proc. EMNLP, 1387–1392. PDF
Parsing graphs with hyperedge replacement grammars. With Jacob Andreas, Daniel Bauer, Karl Moritz Hermann, Bevan Jones and Kevin Knight, 2013. In Proc. ACL, 924–932. PDF BibTeX
Students
Current
Former
- Cindy Xinyi Wang (BS, 2017 → CMU)
- Tomer Levinboim (PhD, 2017 → Google)
- Theerawat Dome Songyot (on leave)
- Hui Zhang (on leave → Facebook Research)
- Ashish Vaswani (PhD, 2014 → Google Brain)
- Victoria Fossum (postdoc → Google)