Michael Hahn

I'm a PhD student at Stanford in the Linguistics Department and the Stanford NLP Group. I am interested in computational linguistics, psycholinguistics, and applying computational techniques to the study of human language processing. Before I came to Stanford, I was at the School of Informatics of the University of Edinburgh, working with Frank Keller. Before that, I studied Mathematics and Computational Linguistics in Tübingen.

Email: mhahn2@stanford.edu
Google Scholar, Twitter, GitHub, CV

Publications

In Preparation

2018
[1]	Modeling Task Effects in Human Reading with Neural Attention (Michael Hahn, Frank Keller), 2018. [bibtex] [preprint] [code]

Refereed Articles and Conference Papers

2021
[21]	Sensitivity as a Complexity Measure for Sequence Classification Tasks (Michael Hahn, Dan Jurafsky, Richard Futrell), In Transactions of the Association for Computational Linguistics (Accepted), 2021. [bibtex] [preprint] [code] [slides]
[20]	Modeling word and morpheme order in natural language as an efficient tradeoff of memory and surprisal (Michael Hahn, Judith Degen, Richard Futrell), In Psychological Review, 2021. [bibtex] [pdf] [preprint] [doi] [code] [supplement] [slides]
2020
[19]	RNNs can generate bounded hierarchical languages with optimal memory (John Hewitt, Michael Hahn, Surya Ganguli, Percy Liang, Christopher D. Manning), In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), 2020. [bibtex] [pdf] [preprint] [code]
[18]	Universals of word order reflect optimization of grammars for efficient communication (Michael Hahn, Dan Jurafsky, Richard Futrell), In Proceedings of the National Academy of Sciences of the United States of America, 2020. [bibtex] [pdf] [code] [supplement]
[17]	Theoretical Limitations of Self-Attention in Neural Sequence Models (Michael Hahn), In Transactions of the Association for Computational Linguistics, volume 8, 2020. [bibtex] [pdf] [preprint] [doi] [slides]
2019
[16]	Tabula nearly rasa: Probing the linguistic knowledge of character-level neural language models trained on unsegmented text (Michael Hahn, Marco Baroni), In Transactions of the Association for Computational Linguistics, volume 7, 2019. [bibtex] [pdf] [preprint] [code]
[15]	Estimating Predictive Rate-Distortion Curves via Neural Variational Inference (Michael Hahn, Richard Futrell), In Entropy, volume 21, 2019. [bibtex] [pdf] [code] [reviews]
[14]	Character-based Surprisal as a Model of Human Reading in the Presence of Errors (Michael Hahn, Frank Keller, Yonatan Bisk, Yonatan Belinkov), In Proceedings of the 41st Annual Meeting of the Cognitive Science Society (CogSci), 2019. [bibtex] [pdf] [preprint] [code]
2018
[13]	An information-theoretic explanation of adjective ordering preferences (Michael Hahn, Judith Degen, Noah Goodman, Dan Jurafsky, and Richard Futrell), In Proceedings of the 40th Annual Meeting of the Cognitive Science Society (CogSci), 2018. [bibtex] [pdf] [code]
[12]	Wreath Products of Distributive Forest Algebras (Michael Hahn, Andreas Krebs, Howard Straubing), In Logic in Computer Science (LICS), 2018. [bibtex] [pdf] [preprint] [code]
2016
[11]	Modeling Human Reading with Neural Attention (Michael Hahn, Frank Keller), In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016. [bibtex] [pdf] [code]
2015
[10]	Visibly Counter Languages and the Structure of NC1 (Michael Hahn, Andreas Krebs, Klaus-Jörn Lange, Michael Ludwig), In Proceedings of Mathematical Foundations of Computer Science (MFCS) 2015, 2015. [bibtex] [pdf]
[9]	Henkin Semantics for Reasoning with Natural Language (Michael Hahn, Frank Richter), In Journal of Language Modeling, volume 3, 2015. [bibtex] [pdf] [code]
2014
[8]	Predication and NP Structure in an Omnipredicative Language: The Case of Khoekhoe (Michael Hahn), In Proceedings of the 21st International Conference on Head-Driven Phrase Structure Grammar (Stefan Müller, ed.), CSLI Publications, 2014. [bibtex] [pdf]
[7]	On deriving semantic representations from dependencies: A practical approach for evaluating meaning in learner corpora (Michael Hahn, Detmar Meurers), In Dependency Theory (Kim Gerdes, Eva Hajicová, Leo Wanner, eds.), IOS Press, 2014. [bibtex]
2013
[6]	CoMeT: Integrating different levels of linguistic modeling for meaning assessment (Niels Ott, Ramon Ziai, Michael Hahn, Detmar Meurers), In Proceedings of the 7th International Workshop on Semantic Evaluation (SemEval), 2013. [bibtex] [pdf]
[5]	Word Order Variation in Khoekhoe (Michael Hahn), In Proceedings of the 20th International Conference on Head-Driven Phrase Structure Grammar (Stefan Müller, ed.), 2013. [bibtex] [pdf]
2012
[4]	Evaluating the Meaning of Answers to Reading Comprehension Questions: A Semantics-Based Approach (Michael Hahn, Detmar Meurers), In Proceedings of the 7th Workshop on Innovative Use of NLP for Building Educational Applications (BEA7), Association for Computational Linguistics, 2012. [bibtex] [pdf]
[3]	Arabic Relativization Patterns: A Unified HPSG Analysis (Michael Hahn), In Proceedings of the 19th International Conference on Head-Driven Phrase Structure Grammar, 2012. [bibtex] [pdf]
2011
[2]	Null Conjuncts and Bound Pronouns in Arabic (Michael Hahn), In The Proceedings of the 18th International Conference on Head-Driven Phrase Structure Grammar, 2011. [bibtex]
[1]	On deriving semantic representations from dependencies: A practical approach for evaluating meaning in learner corpora (Michael Hahn, Detmar Meurers), In Proceedings of the Int. Conference on Dependency Linguistics (Depling 2011), 2011. [bibtex] [pdf]

Presentations

2021

[1]

An Information-Theoretic Explanation of Adjective Ordering Preferences, TExMod2020: Theoretical and Experimental Approaches to Modification. Tübingen, Germany (invited). [slides]

2020

[3]

Theoretical Limitations of Self-Attention in Neural Sequence Models (Michael Hahn), 58th Annual Meeting of the Association for Computational Linguistics, 2020. [slides]

[2]

Tabula nearly rasa: Probing the linguistic knowledge of character-level neural language models trained on unsegmented text (Michael Hahn, Marco Baroni), 58th Annual Meeting of the Association for Computational Linguistics, 2020.

[1]

Lexical Effects in Structural Forgetting: Evidence for Experience-Based Accounts and a Neural Network Model (Michael Hahn, Richard Futrell, Edward Gibson), 33rd Annual CUNY Human Sentence Processing Conference, 2020 (oral). [slides][abstract]

2019

[3]

Character-based Surprisal as a Model of Human Reading in the Presence of Errors (Michael Hahn, Frank Keller, Yonatan Bisk, Yonatan Belinkov), 41st Annual Meeting of the Cognitive Science Society (CogSci), 2019 (oral). [slides]

[2]

Crosslinguistic word orders enable an efficient tradeoff of memory and surprisal (Michael Hahn, Judith Degen, Richard Futrell), 32nd Annual CUNY Conference on Human Sentence Processing, 2019 (oral, 7% acceptance). [slides]

[1]

Testing Functional Explanations of Word Order Universals (Michael Hahn, Richard Futrell), 32nd Annual CUNY Conference on Human Sentence Processing, 2019 (oral, 7% acceptance). [slides]

2018

[4]

Testing Functional Explanations of Word Order Universals (Michael Hahn, Richard Futrell), California Meeting on Psycholinguistics, 2018. [slides]

[3]

An information-theoretic explanation of adjective ordering preferences (Michael Hahn, Judith Degen, Noah Goodman, Dan Jurafsky, Richard Futrell), CogSci, 2018. [poster]

[2]

Wreath Products of Distributive Forest Algebras (Michael Hahn, Andreas Krebs, Howard Straubing), LICS, 2018. [slides]

[2]

Mutual Information Impacts Adjective Ordering Across Languages (Michael Hahn, Richard Futrell, Judith Degen, Dan Jurafsky, Noah Goodman), CUNY, 2018. [poster]

[1]

Exploring Adjective Ordering Preferences via Artificial Language Learning (Michael Hahn, Richard Futrell, Judith Degen), CUNY, 2018. [poster]

2017

[2]

Exploring Adjective Ordering Preferences via Artificial Language Learning (Michael Hahn, Richard Futrell, Judith Degen), California Meeting on Psycholinguistics, 2017.

[1]

Modeling Task Effects in Human Reading with Neural Attention (Michael Hahn, Frank Keller), CUNY, 2017. [slides]

2016

[1]

Modeling Human Reading with Neural Attention (Michael Hahn, Frank Keller), EMNLP, 2016. [slides]

Other material

Vowels in Proto-Modern South Arabian (2012)
This manuscript presents some preliminary ideas regarding the reconstruction of Proto-Modern South Arabian, which is of interest for the reconstruction of Proto-Semitic as a whole. A more thorough analysis will have to wait for a comprehensive documentation of Soqotri, Hobyot, and of dialectal variation within the better-documented languages Mehri and Jibbali.
Focus in Old Chinese (2011)
Gentzens Konsistenzbeweis für die Arithmetik (2011)

I also contributed to the chapters on Chinese, Austronesian, Australian, and various African languages in a book on the languages of the world.