1 code implementation • EMNLP 2021 • Neil Rathi, Michael Hahn, Richard Futrell
Linguistic typology generally divides synthetic languages into groups based on their morphological fusion.
no code implementations • 15 Feb 2024 • Michael Hahn, Mark Rofin
We show theoretically and empirically that this theory unifies a broad array of empirical observations about the learning abilities and biases of transformers, such as their generalization bias towards low sensitivity and low degree, and difficulty in length generalization for PARITY.
1 code implementation • 6 Jun 2023 • Thomas Hikaru Clark, Clara Meister, Tiago Pimentel, Michael Hahn, Ryan Cotterell, Richard Futrell, Roger Levy
Here, we ask whether a pressure for UID may have influenced word order patterns cross-linguistically.
no code implementations • 14 Mar 2023 • Michael Hahn, Navin Goyal
Scaling large language models (LLMs) leads to an emergent capacity to learn in-context from example demonstrations.
1 code implementation • 9 Jun 2022 • Michael Hahn, Yang Xu
Using data from 80 languages in 17 language families and phylogenetic modeling, we demonstrate that languages evolve to balance these pressures, such that word order change is accompanied by change in the frequency distribution of the syntactic structures which speakers communicate to maintain overall efficiency.
1 code implementation • 21 Apr 2021 • Michael Hahn, Dan Jurafsky, Richard Futrell
We introduce a theoretical framework for understanding and predicting the complexity of sequence classification tasks, using a novel extension of the theory of Boolean function sensitivity.
2 code implementations • EMNLP 2020 • John Hewitt, Michael Hahn, Surya Ganguli, Percy Liang, Christopher D. Manning
Recurrent neural networks empirically generate natural language with high syntactic fidelity.
1 code implementation • TACL 2019 • Michael Hahn, Marco Baroni
Recurrent neural networks (RNNs) have reached striking performance in many natural language processing tasks.
no code implementations • TACL 2020 • Michael Hahn
These limitations seem surprising given the practical success of self-attention and the prominent role assigned to hierarchical structure in linguistics, suggesting that natural language can be approximated well with models that are too weak for the formal languages typically assumed in theoretical linguistics.
no code implementations • 2 Feb 2019 • Michael Hahn, Frank Keller, Yonatan Bisk, Yonatan Belinkov
Also, transpositions are more difficult than misspellings, and a high error rate increases difficulty for all words, including correct ones.
no code implementations • 31 Jul 2018 • Michael Hahn, Frank Keller
Research on human reading has long documented that reading behavior shows task-specific effects, but it has been challenging to build general models predicting what reading behavior humans will show in a given task.
no code implementations • EMNLP 2016 • Michael Hahn, Frank Keller
When humans read text, they fixate some words and skip others.