Projects
Neural networks for machine translation Models and algorithms for translation and language modeling using neural networks.
Expressivity of neural sequence models Relating neural sequence models to automata, grammars, circuits, and logics.
Natural language (variety) processing Collaboration with Antonis Anastaspoulos (GMU) and Yulia Tsvetkov (UW). Sponsored by NSF.
Language documentation with an AI helper Collaboration with Antonis Anatasopoulos and Geraldine Walther (GMU). Sponsored by NSF.
Differentiable, probabilistic programming with recursive structured models. Collaboration with Chung-chieh Shan (IU). Sponsored by NSF.
NLP on medieval texts Analysis of Latin texts and language modeling for OCR of Latin manuscsripts. Collaborations with Walter Scheirer and Hildegund Müller. Sponsored by Notre Dame FRSP.
Recent Publications
Brian DuSell and David Chiang.
Learning hierarchical structures with differentiable nondeterministic stacks.
In
Proc. ICLR. 2022.
To appear.
PDF
BibTeX
@inproceedings{dusell+chiang:2022,
author = "DuSell, Brian and Chiang, David",
title = "Learning Hierarchical Structures with Differentiable Nondeterministic Stacks",
booktitle = "Proc. ICLR",
year = "2022",
note = "To appear"
}
Samuel Grieggs, Bingyu Shen, Greta Rauch, Pei Li, Jiaqi Ma, David Chiang, Brian Price, and Walter Scheirer.
Measuring human perception to improve handwritten document transcription.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.
doi:10.1109/TPAMI.2021.3092688.
DOI
BibTeX
@article{grieggs+:tpami2021,
author = "Grieggs, Samuel and Shen, Bingyu and Rauch, Greta and Li, Pei and Ma, Jiaqi and Chiang, David and Price, Brian and Scheirer, Walter",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
title = "Measuring Human Perception to Improve Handwritten Document Transcription",
year = "2021",
doi = "10.1109/TPAMI.2021.3092688"
}
Toan Q. Nguyen, Kenton Murray, and David Chiang.
Data augmentation by concatenation for low-resource translation: a mystery and a solution.
In
Proc. Conference on Spoken Language Translation. 2021.
PDF
BibTeX
@inproceedings{nguyen+:2021,
author = "Nguyen, Toan Q. and Murray, Kenton and Chiang, David",
title = "Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution",
booktitle = "Proc. Conference on Spoken Language Translation",
year = "2021"
}
David Chiang and Colin McDonald.
Syntax-based attention masking for neural machine translation.
In
Proc. NAACL Student Research Workshop. 2021.
PDF
BibTeX
@inproceedings{mcdonald+chiang:2021,
author = "Chiang, David and McDonald, Colin",
title = "Syntax-Based Attention Masking for Neural Machine Translation",
year = "2021",
booktitle = "Proc. NAACL Student Research Workshop"
}
David Chiang, Alexander M. Rush, and Boaz Barak.
Named tensor notation.
2021.
arXiv:2102.13196.
PDF
BibTeX
@misc{chiang+:2021,
author = "Chiang, David and Rush, Alexander M. and Barak, Boaz",
title = "Named Tensor Notation",
year = "2021",
note = "arXiv:2102.13196"
}
David Chiang and Chung-chieh Shan.
Translating recursive probabilistic programs to factor graph grammars.
2020.
Presented at PROBPROG 2020.
PDF
BibTeX
@misc{chiang+shan:2020,
author = "Chiang, David and Shan, Chung-chieh",
title = "Translating Recursive Probabilistic Programs to Factor Graph Grammars",
note = "Presented at PROBPROG 2020",
year = "2020"
}
David Chiang and Darcey Riley.
Factor graph grammars.
In
Proc. NeurIPS, 6648–6658. 2020.
PDF
BibTeX
@inproceedings{chiang+riley:2020,
author = "Chiang, David and Riley, Darcey",
title = "Factor Graph Grammars",
year = "2020",
booktitle = "Proc. NeurIPS",
pages = "6648--6658"
}
Brian DuSell and David Chiang.
Learning context-free languages with nondeterministic stack
RNNs.
In
Proc. CoNLL, 507–519. 2020.
PDF
BibTeX
@inproceedings{dusell+chiang:2020,
author = "DuSell, Brian and Chiang, David",
title = "Learning Context-free Languages with Nondeterministic Stack {RNN}s",
booktitle = "Proc. CoNLL",
year = "2020",
pages = "507--519"
}
Justin DeBenedetto and David Chiang.
Representing unordered data using complex-weighted multiset automata.
In Hal Daumé III and Aarti Singh, editors,
Proc. ICML, volume 119 of Proceedings of Machine Learning Research, 2412–2420. 2020.
PDF
BibTeX
@inproceedings{debenedetto+chiang:icml2020,
author = "DeBenedetto, Justin and Chiang, David",
editor = "III, Hal Daumé and Singh, Aarti",
title = "Representing Unordered Data Using Complex-Weighted Multiset Automata",
booktitle = "Proc. ICML",
pages = "2412--2420",
year = "2020",
volume = "119",
series = "Proceedings of Machine Learning Research",
pdf = "http://proceedings.mlr.press/v119/debenedetto20a/debenedetto20a.pdf"
}
Arturo Argueta and David Chiang.
Accelerating sparse matrix operations in neural networks on graphics processing units.
In
Proc. ACL, 6215–6224. 2019.
PDF
BibTeX
@inproceedings{argueta+chiang:acl2019,
author = "Argueta, Arturo and Chiang, David",
title = "Accelerating Sparse Matrix Operations in Neural Networks on Graphics Processing Units",
booktitle = "Proc. ACL",
year = "2019",
xdoi = "10.18653/v1/P19-1626",
pages = "6215--6224"
}
Antonios Anastasopoulos, Alison Lui, Toan Q. Nguyen, and David Chiang.
Neural machine translation of text from non-native speakers.
In
Proc. NAACL: HLT, volume 1, 3070–3080. 2019.
PDF
BibTeX
@inproceedings{lui+al:naacl2019,
author = "Anastasopoulos, Antonios and Lui, Alison and Nguyen, Toan Q. and Chiang, David",
title = "Neural Machine Translation of Text from Non-Native Speakers",
booktitle = "Proc. NAACL: HLT",
year = "2019",
xdoi = "10.18653/v1/N19-1311",
pages = "3070--3080",
volume = "1"
}
Kenton Murray and David Chiang.
Correcting length bias in neural machine translation.
In
Proc. WMT, 212–223. 2018.
PDF
BibTeX
@inproceedings{murray+chiang:wmt2018,
author = "Murray, Kenton and Chiang, David",
title = "Correcting Length Bias in Neural Machine Translation",
booktitle = "Proc. WMT",
year = "2018",
pages = "212--223",
location = "Belgium, Brussels"
}
Justin DeBenedetto and David Chiang.
Algorithms and training for weighted multiset automata and regular expressions.
In
Proc. Conference on Implementation and Applications of Automata, 146–158. 2018.
PDF
BibTeX
@inproceedings{debenedetto+chiang:2018,
author = "DeBenedetto, Justin and Chiang, David",
title = "Algorithms and Training for Weighted Multiset Automata and Regular Expressions",
booktitle = "Proc. Conference on Implementation and Applications of Automata",
year = "2018",
pages = "146--158"
}
Toan Nguyen and David Chiang.
Improving lexical choice in neural machine translation.
In
Proc. NAACL: HLT, volume 1, 334–343. 2018.
PDF
BibTeX
@inproceedings{nguyen+chiang:naacl2018,
author = "Nguyen, Toan and Chiang, David",
title = "Improving Lexical Choice in Neural Machine Translation",
booktitle = "Proc. NAACL: HLT",
year = "2018",
pages = "334--343",
location = "New Orleans, Louisiana",
volume = "1"
}
Salvador Aguinaga, David Chiang, and Tim Weninger.
Learning hyperedge replacement grammars for graph generation.
IEEE Trans. Pattern Analysis and Machine Intelligence, 41(3):625–638, 2019.
doi:10.1109/TPAMI.2018.2810877.
PDF
BibTeX
@article{aguinaga+:tpami2019,
author = "Aguinaga, Salvador and Chiang, David and Weninger, Tim",
title = "Learning Hyperedge Replacement Grammars for Graph Generation",
journal = "IEEE Trans. Pattern Analysis and Machine Intelligence",
year = "2019",
volume = "41",
number = "3",
pages = "625--638",
doi = "10.1109/TPAMI.2018.2810877"
}
David Chiang, Frank Drewes, Daniel Gildea, Adam Lopez, and Giorgio Satta.
Weighted
DAG automata for semantic graphs.
Computational Linguistics, 44(1):119–186, 2018.
PDF
BibTeX
@article{chiang+:cl2018,
author = "Chiang, David and Drewes, Frank and Gildea, Daniel and Lopez, Adam and Satta, Giorgio",
title = "Weighted {DAG} automata for semantic graphs",
journal = "Computational Linguistics",
year = "2018",
volume = "44",
number = "1",
pages = "119--186"
}
All papers →
