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
Chihiro Taguchi, Yusuke Sakai, Parisa Haghani, and David Chiang.
Universal automatic phonetic transcription into the
International
Phonetic
Alphabet.
In
Proc. INTERSPEECH. 2023.
To appear.
BibTeX
@inproceedings{taguchi+:2023,
author = "Taguchi, Chihiro and Sakai, Yusuke and Haghani, Parisa and Chiang, David",
title = "Universal Automatic Phonetic Transcription into the {I}nternational {P}honetic {A}lphabet",
booktitle = "Proc. INTERSPEECH",
year = "2023",
note = "To appear"
}
Alexandra Butoi, Ryan Cotterell, and David Chiang.
Convergence and diversity in the control hierarchy.
In
Proc. ACL. 2023.
To appear.
PDF
BibTeX
@inproceedings{butoi+:2023,
author = "Butoi, Alexandra and Cotterell, Ryan and Chiang, David",
title = "Convergence and Diversity in the Control Hierarchy",
booktitle = "Proc. ACL",
note = "To appear",
year = "2023"
}
David Chiang, Peter Cholak, and Anand Pillay.
Tighter bounds on the expressivity of transformer encoders.
In
Proc. ICML. 2023.
To appear.
PDF
BibTeX
@inproceedings{chiang+cholak+pillay:2023,
author = "Chiang, David and Cholak, Peter and Pillay, Anand",
title = "Tighter Bounds on the Expressivity of Transformer Encoders",
booktitle = "Proc. ICML",
note = "To appear",
year = "2023"
}
Aarohi Srivastava and David Chiang.
Fine-tuning
BERT with character-level noise for zero-shot transfer to dialects and closely-related languages.
In
Proc. Workshop on NLP for Similar Languages, Varieties and Dialects. 2023.
PDF
BibTeX
@inproceedings{srivastava+chiang:2023fine,
author = "Srivastava, Aarohi and Chiang, David",
title = "Fine-Tuning {BERT} with Character-Level Noise for Zero-Shot Transfer to Dialects and Closely-Related Languages",
year = "2023",
booktitle = "Proc. Workshop on NLP for Similar Languages, Varieties and Dialects",
arxiv_url = "https://arxiv.org/abs/2303.17683"
}
Patrick Soga and David Chiang.
Bridging graph position encodings for transformers with weighted graph-walking automata.
Transactions on Machine Learning Research, 2023.
PDF
BibTeX
@article{soga+chiang:2023,
author = "Soga, Patrick and Chiang, David",
title = "Bridging Graph Position Encodings for Transformers with Weighted Graph-Walking Automata",
year = "2023",
journal = "Transactions on Machine Learning Research"
}
Brian DuSell and David Chiang.
The surprising computational power of nondeterministic stack
RNNs.
In
Proc. ICLR. 2023.
PDF
BibTeX
@inproceedings{dusell+chiang:2023,
author = "DuSell, Brian and Chiang, David",
title = "The Surprising Computational Power of Nondeterministic Stack {RNN}s",
booktitle = "Proc. ICLR",
year = "2023"
}
David Chiang, Colin McDonald, and Chung-chieh Shan.
Exact recursive probabilistic programming.
PACMPL, 2023.
doi:10.1145/3586050.
PDF
BibTeX
@article{chiang+mcdonald+shan:2023,
author = "Chiang, David and McDonald, Colin and Shan, Chung-chieh",
title = "Exact Recursive Probabilistic Programming",
journal = "PACMPL",
volume = "7",
number = "OOPSLA1",
article = "98",
xmonth = "April",
year = "2023",
doi = "10.1145/3586050"
}
Chihiro Taguchi and David Chiang.
Introducing morphology in
Universal
Dependencies
Japanese.
In
Proc. Workshop on Universal Dependencies, 65–72. 2023.
PDF
BibTeX
@inproceedings{taguchi+chiang:2023,
author = "Taguchi, Chihiro and Chiang, David",
title = "Introducing Morphology in {U}niversal {D}ependencies {J}apanese",
year = "2023",
booktitle = "Proc. Workshop on Universal Dependencies",
pages = "65--72"
}
David Chiang, Alexander M. Rush, and Boaz Barak.
Named tensor notation.
Transactions on Machine Learning Research, 2023.
PDF
BibTeX
@article{chiang+rush+barak:2023,
author = "Chiang, David and Rush, Alexander M. and Barak, Boaz",
title = "Named Tensor Notation",
year = "2023",
xmonth = "January",
journal = "Transactions on Machine Learning Research"
}
Chihiro Taguchi.
Mermaid constructions in
Lexical
Functional
Grammar.
In
Proc. LFG, 365–384. 2022.
PDF
BibTeX
@inproceedings{taguchi:2022,
author = "Taguchi, Chihiro",
title = "Mermaid Constructions in {L}exical {F}unctional {G}rammar",
year = "2022",
booktitle = "Proc. LFG",
pages = "365--384"
}
Darcey Riley and David Chiang.
A continuum of generation tasks for investigating length bias and degenerate repetition.
In
Proc. BlackboxNLP. 2022.
PDF
BibTeX
@inproceedings{riley+chiang:2022,
author = "Riley, Darcey and Chiang, David",
title = "A Continuum of Generation Tasks for Investigating Length Bias and Degenerate Repetition",
booktitle = "Proc. BlackboxNLP",
year = "2022"
}
Alexandra Butoi, Brian DuSell, Tim Vieira, Ryan Cotterell, and David Chiang.
Algorithms for weighted pushdown automata.
In
Proc. EMNLP. 2022.
PDF
BibTeX
@inproceedings{butoi+:2022,
author = "Butoi, Alexandra and DuSell, Brian and Vieira, Tim and Cotterell, Ryan and Chiang, David",
title = "Algorithms for Weighted Pushdown Automata",
year = "2022",
booktitle = "Proc. EMNLP"
}
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal Md Shoeb, Abubakar Abid, Adam Fisch, Adam R. Brown, Adam Santoro, Aditya Gupta, Adri
à Garriga-Alonso, and others.
Beyond the
Imitation
Game: quantifying and extrapolating the capabilities of language models.
2022.
arXiv:2206.04615.
PDF
BibTeX
@misc{srivastava+:2022,
author = "Srivastava, Aarohi and Rastogi, Abhinav and Rao, Abhishek and Shoeb, Abu Awal Md and Abid, Abubakar and Fisch, Adam and Brown, Adam R. and Santoro, Adam and Gupta, Aditya and Garriga-Alonso, Adri{\a} and others",
title = "Beyond the {I}mitation {G}ame: Quantifying and extrapolating the capabilities of language models",
year = "2022",
note = "arXiv:2206.04615"
}
David Chiang and Peter Cholak.
Overcoming a theoretical limitation of self-attention.
In
Proc. ACL. 2022.
PDF
BibTeX
@inproceedings{chiang+cholak:2022,
author = "Chiang, David and Cholak, Peter",
title = "Overcoming a Theoretical Limitation of Self-Attention",
booktitle = "Proc. ACL",
year = "2022"
}
Brian DuSell and David Chiang.
Learning hierarchical structures with differentiable nondeterministic stacks.
In
Proc. ICLR. 2022.
PDF
BibTeX
@inproceedings{dusell+chiang:iclr2022,
author = "DuSell, Brian and Chiang, David",
title = "Learning Hierarchical Structures with Differentiable Nondeterministic Stacks",
booktitle = "Proc. ICLR",
year = "2022"
}
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"
}
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"
}
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"
}
All papers →