 What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular LanguagesAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 Recurrent Neural Language Models as Probabilistic Finite-state AutomataConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 Learning Transductions and Alignments with RNN Seq2seq ModelsInternational Conference on Graphics and Interaction (GI), 2023 |
 Algorithms for Acyclic Weighted Finite-State Automata with Failure ArcsConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 The Surprising Computational Power of Nondeterministic Stack RNNsInternational Conference on Learning Representations (ICLR), 2022 |
 A Call for Clarity in Beam Search: How It Works and When It StopsInternational Conference on Language Resources and Evaluation (LREC), 2022 |
 Neuro-Symbolic Language Modeling with Automaton-augmented RetrievalInternational Conference on Machine Learning (ICML), 2022 |
 Saturated Transformers are Constant-Depth Threshold CircuitsTransactions of the Association for Computational Linguistics (TACL), 2021 |
 Random Feature AttentionInternational Conference on Learning Representations (ICLR), 2021 |
 |
 Connecting Weighted Automata, Tensor Networks and Recurrent Neural
Networks through Spectral LearningMachine-mediated learning (ML), 2020 |
 A Formal Hierarchy of RNN ArchitecturesAnnual Meeting of the Association for Computational Linguistics (ACL), 2020 |
 RNN Architecture Learning with Sparse RegularizationConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 PaLM: A Hybrid Parser and Language ModelConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 |
 A Lightweight Recurrent Network for Sequence ModelingAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Interpreting and improving natural-language processing (in machines)
with natural language-processing (in the brain)Neural Information Processing Systems (NeurIPS), 2019 |
 Connecting Weighted Automata and Recurrent Neural Networks through
Spectral LearningInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2018 |
