Curriculum Vitae

Education

Honors and awards

Professional experience

Advising and Thesis Commitees

Courses Taught

Publications

Journal articles

Lena Strobl, Dana Angluin, David Chiang, Jonathan Rawski, and Ashish Sabharwal. Transformers as transducers. Transactions of the Association for Computational Linguistics, 2024. To appear.
Lena Strobl, William Merrill, Gail Weiss, David Chiang, and Dana Angluin. What formal languages can transformers express? A survey. Transactions of the Association for Computational Linguistics, 12:543–561, 2024. doi:10.1162/tacl_a_00663.
Patrick Soga and David Chiang. Bridging graph position encodings for transformers with weighted graph-walking automata. Transactions on Machine Learning Research, 2023.
David Chiang, Colin McDonald, and Chung-chieh Shan. Exact recursive probabilistic programming. PACMPL, 2023. doi:10.1145/3586050.
David Chiang, Alexander M. Rush, and Boaz Barak. Named tensor notation. Transactions on Machine Learning Research, January 2023.
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.
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.
David Chiang, Frank Drewes, Daniel Gildea, Adam Lopez, and Giorgio Satta. Weighted DAG automata for semantic graphs. Computational Linguistics, 44(1):119–186, 2018.
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, 32(1–2):59–89, 2018. doi:10.1007/s10590-017-9207-1.
Steven Bird, David Chiang, Friedel Frowein, Florian Hanke, and Ashish Vaswani. Documentary linguistics and computational linguistics: a response to Brooks. Language Documentation and Conservation, 9:10–11, 2015.
Yuval Marton, David Chiang, and Philip Resnik. Soft syntactic constraints for Arabic-English hierarchical phrase-based translation. Machine Translation, 26(1–2):137–157, 2012. doi:10.1007/s10590-011-9111-z.
Steven Bird, David Chiang, Friedel Frowein, Andrea L. Berez, Mark Eby, Florian Hanke, Ryan Shelby, Ashish Vaswani, and Ada Wan. The International Workshop on Language Preservation: an experiment in text collection and language technology. Language Documentation and Conservation, pages 155–167, 2013.
David Chiang. Hope and fear for discriminative training of statistical translation models. J. Machine Learning Research, 13:1159–1187, 2012. A few typos corrected, in particular in the definition of the loss function.
Ken A. Dill, Adam Lucas, Julia Hockenmaier, Liang Huang, David Chiang, and Aravind K. Joshi. Computational linguistics: a new tool for exploring biopolymer structures and statistical mechanics. Polymer, 48(15):4289–4300, 2007. doi:10.1016/j.polymer.2007.05.018.
David Chiang. Hierachical phrase-based translation. Computational Linguistics, 33(2):201–228, 2007. doi:10.1162/coli.2007.33.2.201.
David Chiang, Aravind K. Joshi, and Ken A. Dill. A grammatical theory for the conformational changes of simple helix bundles. J. Computational Biology, 13(1):21–42, 2006. doi:10.1089/cmb.2006.13.21.
David Chiang, Aravind K. Joshi, and David B. Searls. Grammatical representations of macromolecular structure. J. Computational Biology, 13(5):1077–1100, 2006. doi:10.1089/cmb.2006.13.1077.
Mark Dras, David Chiang, and William Schuler. On relations of constituency and dependency grammars. Research on Language and Computation, 2:281–305, 2004.

Books and book chapters

David Chiang. Grammars for Language and Genes: Theoretical and Empirical Investigations. Theory and Applications of Natural Language Processing. Springer, 2012.
David Chiang. Statistical parsing with an automatically extracted tree adjoining grammar. In Rens Bod, Remko Scha, and Khalil Sima'an, editors, Data Oriented Parsing, pages 299–316. CSLI Publications, Stanford, 2003.

Refereed conference papers

Andy Yang, David Chiang, and Dana Angluin. Masked hard-attention transformers recognize exactly the star-free languages. In Proc. NeurIPS. 2024. To appear.
Ken Sible and David Chiang. Improving rare word translation with dictionaries and attention masking. In Proc. AMTA. 2024.
Andy Yang and David Chiang. Counting like transformers: compiling temporal counting logic into softmax transformers. In Proc. CoLM. 2024.
Chihiro Taguchi and David Chiang. Language complexity and speech recognition accuracy: orthographic complexity hurts, phonological complexity doesn't. In Proc. ACL. 2024. Outstanding Paper Award and Senior Area Chair Award.
Fahim Faisal, Orevaoghene Ahia, Aarohi Srivastava, Kabir Ahuja, David Chiang, Yulia Tsvetkov, and Antonios Anastasopoulos. DIALECTBENCH: a NLP benchmark for dialects, varieties, and closely-related languages. In Proc. ACL. 2024. Social Impact Award.
Stephen Bothwell, Brian DuSell, David Chiang, and Brian Krostenko. PILA: a historical-linguistic dataset of Proto-Italic and Latin. In Proc. LREC-COLING, 12749–12760. 2024.
Chihiro Taguchi, Jefferson Saransig, Dayana Velásquez, and David Chiang. KILLKAN: the automatic speech recognition dataset for Kichwa with morphosyntactic information. In Proc. LREC-COLING, 9753–9763. 2024.
Brian DuSell and David Chiang. Stack attention: improving the ability of transformers to model hierarchical patterns. In Proc. ICLR. 2024. Spotlight paper.
Stephen Bothwell, Justin DeBenedetto, Theresa Crnkovich, Hildegund Müller, and David Chiang. Introducing rhetorical parallelism detection: a new task with datasets, metrics, and baselines. In Proc. EMNLP, 5007–5039. 2023. doi:10.18653/v1/2023.emnlp-main.305.
Alexandra Butoi, Tim Vieira, Ryan Cotterell, and David Chiang. Efficient algorithms for recognizing weighted tree-adjoining languages. In Proc. EMNLP. 2023.
Aarohi Srivastava and David Chiang. BERTwich: extending BERT's capabilities to model dialectal and noisy text. In Findings of ACL: EMNLP. 2023.
Chihiro Taguchi, Yusuke Sakai, Parisa Haghani, and David Chiang. Universal automatic phonetic transcription into the International Phonetic Alphabet. In Proc. INTERSPEECH. 2023. doi:10.21437/Interspeech.2023-2584.
Alexandra Butoi, Ryan Cotterell, and David Chiang. Convergence and diversity in the control hierarchy. In Proc. ACL. 2023.
David Chiang, Peter Cholak, and Anand Pillay. Tighter bounds on the expressivity of transformer encoders. In Proc. ICML, 5544–5562. 2023.
Brian DuSell and David Chiang. The surprising computational power of nondeterministic stack RNNs. In Proc. ICLR. 2023.
Alexandra Butoi, Brian DuSell, Tim Vieira, Ryan Cotterell, and David Chiang. Algorithms for weighted pushdown automata. In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang, editors, Proc. EMNLP, 9669–9680. 2022. doi:10.18653/v1/2022.emnlp-main.656.
David Chiang and Peter Cholak. Overcoming a theoretical limitation of self-attention. In Smaranda Muresan, Preslav Nakov, and Aline Villavicencio, editors, Proc. ACL, volume 1, 7654–7664. 2022. doi:10.18653/v1/2022.acl-long.527.
Brian DuSell and David Chiang. Learning hierarchical structures with differentiable nondeterministic stacks. In Proc. ICLR. 2022. Spotlight paper.
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.
David Chiang and Darcey Riley. Factor graph grammars. In Proc. NeurIPS, 6648–6658. 2020. Spotlight paper.
Brian DuSell and David Chiang. Learning context-free languages with nondeterministic stack RNNs. In Proc. CoNLL, 507–519. 2020.
Justin DeBenedetto and David Chiang. Representing unordered data using complex-weighted multiset automata. In Proc. ICML, 2412–2420. 2020.
Arturo Argueta and David Chiang. Accelerating sparse matrix operations in neural networks on graphics processing units. In Proc. ACL, 6215–6224. 2019.
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.
Kenton Murray and David Chiang. Correcting length bias in neural machine translation. In Proc. WMT, 212–223. 2018.
Antonios Anastasopoulos, Marika Lekakou, Josep Quer, Eleni Zimianiti, Justin DeBenedetto, and David Chiang. Part-of-speech tagging on an endangered language: a parallel Griko-Italian resource. In Proc. COLING, 2529–2539. 2018.
Arturo Argueta and David Chiang. Composing finite state transducers on GPUs. In Proc. ACL, 2697–2705. 2018.
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.
Antonios Anastasopoulos and David Chiang. Leveraging translations for speech transcription in low-resource settings. In Proc. INTERSPEECH. 2018.
Corey Pennycuff, Satyaki Sikdar, Catalina Vajiac, David Chiang, and Tim Weninger. Synchronous hyperedge replacement graph grammars. In Proc. Conference on Graph Transformations. 2018.
Antonios Anastasopoulos and David Chiang. Tied multitask learning for neural speech translation. In Proc. NAACL: HLT, volume 1, 82–91. 2018.
Toan Nguyen and David Chiang. Improving lexical choice in neural machine translation. In Proc. NAACL: HLT, volume 1, 334–343. 2018.
Huadong Chen, Shujian Huang, David Chiang, Xinyu Dai, and Jiajun Chen. Combining character and word information in neural machine translation using a multi-level attention. In Proc. NAACL: HLT, volume 1, 1284–1293. 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.
Huadong Chen, Shujian Huang, David Chiang, Xin-Yu Dai, and Jiajun Chen. Top-rank enhanced listwise optimization for statistical machine translation. In Proc. CoNLL, 90–99. 2017.
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.
Arturo Argueta and David Chiang. Decoding with finite-state transducers on GPUs. In Proc. EACL, volume 1, 1044–1052. 2017.
Antonios Anastasopoulos, David Chiang, and Long Duong. An unsupervised probability model for speech-to-translation alignment of low-resource languages. In Proc. EMNLP, 1255–1263. 2016.
Salvador Aguiñaga, Rodrigo Palacios, David Chiang, and Tim Weninger. Growing graphs from hyperedge replacement graph grammars. In Proc. CIKM, 469–478. 2016. doi:10.1145/2983323.2983826.
Long Duong, Antonios Anastasopoulos, David Chiang, Steven Bird, and Trevor Cohn. An attentional model for speech translation without transcription. In Proc. NAACL: HLT, 949–959. 2016.
Tomer Levinboim and David Chiang. Supervised phrase table triangulation with neural word embeddings for low-resource languages. In Proc. EMNLP, 1079–1083. 2015.
Tomer Levinboim and David Chiang. Multi-task word alignment triangulation for low-resource languages. In Proc. NAACL: HLT, 1221–1226. 2015.
Kenton Murray and David Chiang. Auto-sizing neural networks: with applications to \(n\)-gram language models. In Proc. EMNLP, 908–916. 2015.
Tomer Levinboim, Ashish Vaswani, and David Chiang. Model invertibility regularization: sequence alignment with or without parallel data. In Proc. NAACL: HLT, 609–618. 2015.
Theerawat Songyot and David Chiang. Improving word alignment using word similarity. In Proc. EMNLP, 1840–1845. 2014.
Hui Zhang and David Chiang. Kneser-Ney smoothing on expected counts. In Proc. ACL, volume 1, 765–774. 2014.
Ashish Vaswani, Yinggong Zhao, Victoria Fossum, and David Chiang. Decoding with large-scale neural language models improves translation. In Proc. EMNLP, 1387–1392. 2013.
David Chiang, Jacob Andreas, Daniel Bauer, Karl Moritz Hermann, Bevan Jones, and Kevin Knight. Parsing graphs with hyperedge replacement grammars. In Proc. ACL, volume 1, 924–932. 2013.
Steven Bird and David Chiang. Machine translation for language preservation. In Proc. COLING, 125–134. 2012.
Ashish Vaswani, Liang Huang, and David Chiang. Smaller alignment models for better translations: unsupervised word alignment with the \(\ell _0\)-norm. In Proc. ACL, volume 1, 311–319. 2012.
Hui Zhang and David Chiang. An exploration of forest-to-string translation: does translation help or hurt parsing? In Proc. ACL, volume 2, 317–321. 2012.
Ashish Vaswani, Haitao Mi, Liang Huang, and David Chiang. Rule Markov models for fast tree-to-string translation. In Proc. ACL: HLT, 856–864. 2011.
Dirk Hovy, Ashish Vaswani, Stephen Tratz, David Chiang, and Eduard Hovy. Models and training for unsupervised preposition sense disambiguation. In Proc. ACL: HLT, 323–328. 2011.
David Chiang, Steve DeNeefe, and Michael Pust. Two easy improvements to lexical weighting. In Proc. ACL: HLT, 455–460. 2011.
Shu Cai, David Chiang, and Yoav Goldberg. Language-independent parsing with empty elements. In Proc. ACL: HLT, 212–216. 2011.
Ashish Vaswani, Adam Pauls, and David Chiang. Efficient optimization of an MDL-inspired objective function for unsupervised part-of-speech tagging. In Proc. ACL, 209–214. 2010.
David Chiang. Learning to translate with source and target syntax. In Proc. ACL, 1443–1452. 2010.
David Chiang, Jonathan Graehl, Kevin Knight, Adam Pauls, and Sujith Ravi. Bayesian inference for finite-state transducers. In HLT: NAACL, 447–455. 2010.
Adam Pauls, Dan Klein, David Chiang, and Kevin Knight. Unsupervised syntactic alignment with inversion transduction grammars. In HLT: NAACL, 118–126. 2010.
Sujith Ravi, Ashish Vaswani, Kevin Knight, and David Chiang. Fast, greedy model minimization for unsupervised tagging. In Proc. COLING, 940–948. 2010.
John DeNero, David Chiang, and Kevin Knight. Fast consensus decoding over translation forests. In Proc. ACL-IJCNLP, 567–575. 2009.
David Chiang, Kevin Knight, and Wei Wang. 11,001 new features for statistical machine translation. In Proc. HLT: NAACL, 218–226. 2009. Best Paper Award.
David Chiang, Steve DeNeefe, Yee Seng Chan, and Hwee Tou Ng. Decomposability of translation metrics for improved evaluation and efficient algorithms. In Proc. EMNLP, 610–619. 2008.
David Chiang, Yuval Marton, and Philip Resnik. Online large-margin training of syntactic and structural translation features. In Proc. EMNLP, 224–233. 2008.
Hao Zhang, Daniel Gildea, and David Chiang. Extracting synchronous grammar rules from word-level alignments in linear time. In Proc. COLING, 1081–1088. 2008.
Liang Huang and David Chiang. Forest rescoring: faster decoding with integrated language models. In Proc. ACL, 144–151. 2007.
Yee Seng Chan, Hwee Tou Ng, and David Chiang. Word sense disambiguation improves statistical machine translation. In Proc. ACL, 33–40. 2007.
David Chiang, Mona Diab, Nizar Habash, Owen Rambow, and Safiullah Shareef. Parsing Arabic dialects. In Proc. EACL. 2006.
David Chiang, Adam Lopez, Nitin Madnani, Christof Monz, Philip Resnik, and Michael Subotin. The Hiero machine translation system: extensions, evaluation, and analysis. In Proc. HLT-EMNLP, 779–786. 2005.
David Chiang. A hierarchical phrase-based model for statistical machine translation. In Proc. ACL, 263–270. 2005. doi:10.3115/1219840.1219873. Best Paper Award.
David Chiang. Mildly context sensitive grammars for estimating maximum entropy models. In Gerald Penn, editor, Proc. Conference on Formal Grammar. 2003.
David Chiang and Aravind K. Joshi. Formal grammars for estimating partition functions of double-stranded chain molecules. In Proc. HLT, 63–67. 2002.
David Chiang and Daniel M. Bikel. Recovering latent information in treebanks. In Proc. COLING. 2002.
David Chiang. Constraints on strong generative power. In Proc. ACL, 132–139. 2001. doi:10.3115/1073012.1073030.
Fudong Chiou, David Chiang, and Martha Palmer. Facilitating treebank annotation using a statistical parser. In Proc. HLT. 2001.
David Chiang. Statistical parsing with an automatically-extracted tree adjoining grammar. In Proc. ACL, 456–463. 2000. doi:10.3115/1075218.1075276.
William Schuler, David Chiang, and Mark Dras. Multi-component TAG and notions of formal power. In Proc. ACL, 448–455. 2000. doi:10.3115/1075218.1075275.

Refereed workshop papers

Stephen Bothwell, Abigail Swenor, and David Chiang. Nostra Domina at EvaLatin 2024: improving Latin polarity detection through data augmentation. In Proc. Workshop on Language Technologies for Historical and Ancient Languages, 215–222. 2024.
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.
Chihiro Taguchi and David Chiang. Introducing morphology in Universal Dependencies Japanese. In Proc. Workshop on Universal Dependencies, 65–72. 2023.
Darcey Riley and David Chiang. A continuum of generation tasks for investigating length bias and degenerate repetition. In Proc. BlackboxNLP. 2022.
Colin McDonald and David Chiang. Syntax-based attention masking for neural machine translation. In Proc. NAACL Student Research Workshop. 2021.
Kenton Murray, Jeffery Kinnison, Toan Q. Nguyen, Walter Scheirer, and David Chiang. Auto-sizing the Transformer network: improving speed, efficiency, and performance for low-resource machine translation. In Proc. Workshop on Neural Generation and Translation, 231–240. 2019.
Kenton Murray, Brian DuSell, and David Chiang. Efficiency through auto-sizing: Notre Dame NLP's submission to the WNGT 2019 efficiency task. In Proc. Workshop on Neural Generation and Translation, 297–301. 2019. doi:10.18653/v1/D19-5634.
Xinyi Wang, Salvador Aguinaga, Tim Weninger, and David Chiang. Growing better graphs with latent-variable probabilistic graph grammars. In Proc. Workshop on Mining and Learning with Grammars. 2018.
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.
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.
David Chiang and Tatjana Scheffler. Flexible composition and delayed tree-locality. In Proc. TAG+, 17–24. 2008.
David Chiang and Owen Rambow. The hidden TAG model: synchronous grammars for parsing resource-poor languages. In Proc. TAG+, 1–8. 2006.
David Chiang. The weak generative capacity of linear tree-adjoining grammars. In Proc. TAG+, 25–32. 2006.
Liang Huang and David Chiang. Better \(k\)-best parsing. In Proc. IWPT, 53–64. 2005.
David Chiang. Uses and abuses of intersected languages. In Proc. TAG+, 9–15. 2004.
David Chiang. Putting some weakly context-free formalisms in order. In Proc. TAG+, 11–18. 2002.
Daniel M. Bikel and David Chiang. Two statistical parsing models applied to the Chinese Treebank. In Proc. Chinese Language Processing Workshop, 1–6. 2000. doi:10.3115/1117769.1117771.
David Chiang, William Schuler, and Mark Dras. Some remarks on an extension of synchronous TAG. In Proc. TAG+, 61–66. 2000.
Mark Dras, David Chiang, and William Schuler. A multi-level TAG approach to dependency. In Proc. ESSLLI Workshop on Linguistic Theory and Grammar Implementation, 33–46. 2000.

Invited presentations

Grants awarded

Professional activities

Other information