David Chiang

Dialect Matters: Cross-Lingual ASR Transfer for Low-Resource Indic Language Varieties EACL 2026 We’re Calling an Intervention: Exploring Fundamental Hurdles in Adapting Language Models to Nonstandard Text NAACL 2025 Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark EMNLP 2025 PILA: A Historical-Linguistic Dataset of Proto-Italic and Latin COLING 2024 Nostra Domina at EvaLatin 2024: Improving Latin Polarity Detection through Data Augmentation COLING 2024 Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns ICLR 2024 Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages NIPS 2024 DIALECTBENCH: An NLP Benchmark for Dialects, Varieties, and Closely-Related Languages ACL 2024 Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn’t ACL 2024 Killkan: The Automatic Speech Recognition Dataset for Kichwa with Morphosyntactic Information COLING 2024 Fine-Tuning BERT with Character-Level Noise for Zero-Shot Transfer to Dialects and Closely-Related Languages EACL 2023 Tighter Bounds on the Expressivity of Transformer Encoders ICML 2023 Efficient Algorithms for Recognizing Weighted Tree-Adjoining Languages EMNLP 2023 Introducing Rhetorical Parallelism Detection: A New Task with Datasets, Metrics, and Baselines EMNLP 2023 Convergence and Diversity in the Control Hierarchy ACL 2023 The Surprising Computational Power of Nondeterministic Stack RNNs ICLR 2023 Universal Automatic Phonetic Transcription into the International Phonetic Alphabet INTERSPEECH 2023 BERTwich: Extending BERT’s Capabilities to Model Dialectal and Noisy Text EMNLP 2023 Overcoming a Theoretical Limitation of Self-Attention ACL 2022 Learning Hierarchical Structures with Differentiable Nondeterministic Stacks ICLR 2022 A Continuum of Generation Tasks for Investigating Length Bias and Degenerate Repetition EMNLP 2022 Algorithms for Weighted Pushdown Automata EMNLP 2022 Syntax-Based Attention Masking for Neural Machine Translation NAACL 2021 Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution IJCNLP 2021 Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution ACL 2021 Learning Context-free Languages with Nondeterministic Stack RNNs EMNLP 2020 Learning Context-free Languages with Nondeterministic Stack RNNs CONLL 2020 Factor Graph Grammars NIPS 2020 [RETRACTED] Look It Up: Bilingual and Monolingual Dictionaries Improve Neural Machine Translation EMNLP 2020 Representing Unordered Data Using Complex-Weighted Multiset Automata ICML 2020 Accelerating Sparse Matrix Operations in Neural Networks on Graphics Processing Units ACL 2019 Auto-Sizing the Transformer Network: Improving Speed, Efficiency, and Performance for Low-Resource Machine Translation EMNLP 2019 Efficiency through Auto-Sizing: Notre Dame NLP’s Submission to the WNGT 2019 Efficiency Task EMNLP 2019 Neural Machine Translation of Text from Non-Native Speakers NAACL 2019 Part-of-Speech Tagging on an Endangered Language: a Parallel Griko-Italian Resource COLING 2018 Composing Finite State Transducers on GPUs ACL 2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing EMNLP 2018 Correcting Length Bias in Neural Machine Translation EMNLP 2018 Leveraging Translations for Speech Transcription in Low-resource Settings INTERSPEECH 2018 Tied Multitask Learning for Neural Speech Translation NAACL 2018 Improving Lexical Choice in Neural Machine Translation NAACL 2018 Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention NAACL 2018 Top-Rank Enhanced Listwise Optimization for Statistical Machine Translation CONLL 2017 Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder ACL 2017 Decoding with Finite-State Transducers on GPUs EACL 2017 Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation IJCNLP 2017 An Unsupervised Probability Model for Speech-to-Translation Alignment of Low-Resource Languages EMNLP 2016 An Attentional Model for Speech Translation Without Transcription NAACL 2016 Model Invertibility Regularization: Sequence Alignment With or Without Parallel Data NAACL 2015 Auto-Sizing Neural Networks: With Applications to n-gram Language Models EMNLP 2015 Supervised Phrase Table Triangulation with Neural Word Embeddings for Low-Resource Languages EMNLP 2015 Multi-Task Word Alignment Triangulation for Low-Resource Languages NAACL 2015 Improving Word Alignment using Word Similarity EMNLP 2014 Kneser-Ney Smoothing on Expected Counts ACL 2014 Decoding with Large-Scale Neural Language Models Improves Translation EMNLP 2013 Parsing Graphs with Hyperedge Replacement Grammars ACL 2013 Machine Translation for Language Preservation COLING 2012 An Exploration of Forest-to-String Translation: Does Translation Help or Hurt Parsing? ACL 2012 Smaller Alignment Models for Better Translations: Unsupervised Word Alignment with the l0-norm ACL 2012 Hope and Fear for Discriminative Training of Statistical Translation Models JMLR 2012 Language-Independent Parsing with Empty Elements ACL 2011 Rule Markov Models for Fast Tree-to-String Translation ACL 2011 Two Easy Improvements to Lexical Weighting ACL 2011 Models and Training for Unsupervised Preposition Sense Disambiguation ACL 2011 Bayesian Inference for Finite-State Transducers NAACL 2010 Efficient Optimization of an MDL-Inspired Objective Function for Unsupervised Part-Of-Speech Tagging ACL 2010 Learning to Translate with Source and Target Syntax ACL 2010 Unsupervised Syntactic Alignment with Inversion Transduction Grammars NAACL 2010 Fast, Greedy Model Minimization for Unsupervised Tagging COLING 2010 Fast Consensus Decoding over Translation Forests ACL 2009 Fast Consensus Decoding over Translation Forests IJCNLP 2009 11,001 New Features for Statistical Machine Translation NAACL 2009 Extracting Synchronous Grammar Rules From Word-Level Alignments in Linear Time COLING 2008 Decomposability of Translation Metrics for Improved Evaluation and Efficient Algorithms EMNLP 2008 Online Large-Margin Training of Syntactic and Structural Translation Features EMNLP 2008 Word Sense Disambiguation Improves Statistical Machine Translation ACL 2007 Forest Rescoring: Faster Decoding with Integrated Language Models ACL 2007 Parsing Arabic Dialects EACL 2006 A Hierarchical Phrase-Based Model for Statistical Machine Translation ACL 2005 The Hiero Machine Translation System: Extensions, Evaluation, and Analysis EMNLP 2005 Recovering Latent Information in Treebanks COLING 2002 Constraints on Strong Generative Power ACL 2001 Statistical Parsing with an Automatically-Extracted Tree Adjoining Grammar ACL 2000 Multi-Component TAG and Notions of Formal Power ACL 2000 Two Statistical Parsing Models Applied to the Chinese Treebank ACL 2000