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 2018: CSE 40/60657, Natural Language Processing.
Spring 2018: CSE 30151, Theory of Computing.
Fall 2017: CSE 40/60657, Natural Language Processing.

Recent and selected publications

Antonios Anastasopoulos and David Chiang. Tied multitask learning for neural speech translation. In Proc. NAACL HLT. 2018. To appear. PDF BibTeX

    @inproceedings{anastasopoulos+chiang:naacl2018,
        author = "Anastasopoulos, Antonios and Chiang, David",
        title = "Tied Multitask Learning for Neural Speech Translation",
        year = "2018",
        note = "To appear",
        booktitle = "Proc. NAACL HLT"
    }

Toan Nguyen and David Chiang. Improving lexical choice in neural machine translation. In Proc. NAACL HLT. 2018. To appear. PDF BibTeX

    @inproceedings{nguyen+chiang:naacl2018,
        author = "Nguyen, Toan and Chiang, David",
        title = "Improving Lexical Choice in Neural Machine Translation",
        year = "2018",
        note = "To appear",
        booktitle = "Proc. NAACL HLT"
    }

Huadong Chen, Shujian Huang, David Chiang, Xin-Yu Dai, and Jiajun Chen. Combining character and word information in neural machine translation using a multi-level attention. In Proc. NAACL HLT. 2018. To appear. BibTeX

    @inproceedings{chen+:naacl2018,
        author = "Chen, Huadong and Huang, Shujian and Chiang, David and Dai, Xin-Yu and Chen, Jiajun",
        title = "Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention",
        year = "2018",
        note = "To appear",
        booktitle = "Proc. NAACL HLT"
    }

Tim Weninger Salvador Aguinaga, David Chiang. Learning hyperedge replacement grammars for graph generation. IEEE Trans. Pattern Analysis and Machine Intelligence, 2018. To appear. PDF BibTeX

    @article{aguinaga+:tpami2018,
        author = "Salvador Aguinaga, David Chiang, Tim Weninger",
        title = "Learning Hyperedge Replacement Grammars for Graph Generation",
        journal = "IEEE Trans. Pattern Analysis and Machine Intelligence",
        note = "To appear",
        year = "2018"
    }

David Chiang, Frank Drewes, Adam Lopez, and Giorgio Satta. Weighted DAG automata for semantic graphs. Computational Linguistics, 2018. To appear. PDF BibTeX

    @article{chiang+:cl2018,
        author = "Chiang, David and Drewes, Frank and Lopez, Adam and Satta, Giorgio",
        title = "Weighted {DAG} automata for semantic graphs",
        journal = "Computational Linguistics",
        note = "To appear",
        year = "2018"
    }

Toan Q. Nguyen and David Chiang. Transfer learning across low-resource, related languages for neural machine translation. In Proc. IJCNLP, volume 2, 296–301. 2017. PDF BibTeX

    @inproceedings{nguyen-chiang:2017:I17-2,
        author = "Nguyen, Toan Q. and Chiang, David",
        title = "Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation",
        booktitle = "Proc. IJCNLP",
        year = "2017",
        pages = "296--301",
        volume = "2"
    }

Antonios Anastasopoulos, Sameer Bansal, David Chiang, Sharon Goldwater, and Adam Lopez. Spoken term discovery for language documentation using translations. In Proc. Workshop on Speech-Centric NLP, 53–58. 2017. PDF BibTeX

    @inproceedings{anastasopoulos-EtAl:2017:Speech-Centric,
        author = "Anastasopoulos, Antonios and Bansal, Sameer and Chiang, David and Goldwater, Sharon and Lopez, Adam",
        title = "Spoken Term Discovery for Language Documentation using Translations",
        booktitle = "Proc. Workshop on Speech-Centric NLP",
        year = "2017",
        pages = "53--58"
    }

Antonios Anastasopoulos and David Chiang. A case study on using speech-to-translation alignments for language documentation. In Proc. Workshop on Use of Computational Methods in Study of Endangered Languages, 170–178. 2017. PDF BibTeX

    @inproceedings{anastasopoulos-chiang:2017:W17-01,
        author = "Anastasopoulos, Antonios and Chiang, David",
        title = "A case study on using speech-to-translation alignments for language documentation",
        booktitle = "Proc. Workshop on Use of Computational Methods in Study of Endangered Languages",
        year = "2017",
        pages = "170--178"
    }

Huadong Chen, Shujian Huang, David Chiang, and Jiajun Chen. Improved neural machine translation with a syntax-aware encoder and decoder. In Proc. ACL, volume 1, 1936–1945. 2017. PDF BibTeX

    @inproceedings{chen-EtAl:2017:Long6,
        author = "Chen, Huadong and Huang, Shujian and Chiang, David and Chen, Jiajun",
        title = "Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder",
        booktitle = "Proc. ACL",
        year = "2017",
        pages = "1936--1945",
        volume = "1"
    }

Arturo Argueta and David Chiang. Decoding with finite-state transducers on GPUs. In Proc. EACL, volume 1, 1044–1052. 2017. PDF BibTeX

    @inproceedings{argueta-chiang:2017:EACLlong,
        author = "Argueta, Arturo and Chiang, David",
        title = "Decoding with Finite-State Transducers on {GPUs}",
        booktitle = "Proc. EACL",
        year = "2017",
        pages = "1044--1052",
        volume = "1"
    }

Ulf Hermjakob, Qiang Li, Daniel Marcu, Jonathan May, Sebastian J. Mielke, Nima Pourdamghani, Michael Pust, Xing Shi, Kevin Knight, Tomer Levinboim, Kenton Murray, David Chiang, Boliang Zhang, Xiaoman Pan, Di Lu, Ying Lin, and Heng Ji. Incident-driven machine translation and name tagging for low-resource languages. Machine Translation, 2017. PDF BibTeX

    @article{hermjakob+:mt2017,
        author = "Hermjakob, Ulf and Li, Qiang and Marcu, Daniel and May, Jonathan and Mielke, Sebastian J. and Pourdamghani, Nima and Pust, Michael and Shi, Xing and Knight, Kevin and Levinboim, Tomer and Murray, Kenton and Chiang, David and Zhang, Boliang and Pan, Xiaoman and Lu, Di and Lin, Ying and Ji, Heng",
        title = "Incident-Driven Machine Translation and Name Tagging for Low-resource Languages",
        journal = "Machine Translation",
        year = "2017"
    }

full list

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)