Robert Frank

About

Robert Frank is a professor of Linguistics at Yale University. He received his PhD in 1992 from the University of Pennsylvania in Computer and Information Science. His research explores computational models of language learning and processing as well as the role of computational constraints in linguistic explanation. He has worked extensively on the application of the Tree Adjoining Grammar formalism in syntactic theory. Before coming to Yale, he held positions at Johns Hopkins University in Cognitive Science and at the University of Delaware in Linguistics.

Research topics

• Artificial Intelligence
• Computer Science
• Natural Language Processing
• Mathematics
• Machine Learning
• Statistics
• Data science
• Psychology
• Geography

Selected publications

• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

  arXiv (Cornell University) · 2022 · 548 citations

  Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models. To address this challenge, we introduce the Beyon…

  DOI

• Probabilistic Predictions of People Perusing: Evaluating Metrics of Language Model Performance for Psycholinguistic Modeling

  2020 · 47 citations

  Senior authorCorresponding

  By positing a relationship between naturalistic reading times and information-theoretic surprisal, surprisal theory This paper re-evaluates a claim due to Goodkind and Bicknell ( By extending Goodkind and Bicknell's analysis to modern neural architectures, we show that the proposed relation does not always hold for Long Short-Term Memory networks, Transformers, and pre-trained models. We introduce an alternate measure of language modeling performance called predictability norm correlation based…

  DOI

• Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity

  Transactions of the Association for Computational Linguistics · 2022-01-01 · 22 citations

  articleOpen accessSenior authorCorresponding

  Abstract This paper analyzes three formal models of Transformer encoders that differ in the form of their self-attention mechanism: unique hard attention (UHAT); generalized unique hard attention (GUHAT), which generalizes UHAT; and averaging hard attention (AHAT). We show that UHAT and GUHAT Transformers, viewed as string acceptors, can only recognize formal languages in the complexity class AC0, the class of languages recognizable by families of Boolean circuits of constant depth and polynomia…

  PublisherOA PDFDOI

• How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speech

  2023-01-01 · 17 citations

  articleOpen access

  When acquiring syntax, children consistently choose hierarchical rules over competing non-hierarchical possibilities. Is this preference due to a learning bias for hierarchical structure, or due to more general biases that interact with hierarchical cues in children's linguistic input? We explore these possibilities by training LSTMs and Transformers - two types of neural networks without a hierarchical bias - on data similar in quantity and content to children's linguistic input: text from the…

  PublisherOA PDFDOI

• How Abstract Is Linguistic Generalization in Large Language Models? Experiments with Argument Structure

  Transactions of the Association for Computational Linguistics · 2023-01-01 · 12 citations

  articleOpen accessSenior authorCorresponding

  Abstract Language models are typically evaluated on their success at predicting the distribution of specific words in specific contexts. Yet linguistic knowledge also encodes relationships between contexts, allowing inferences between word distributions. We investigate the degree to which pre-trained transformer-based large language models (LLMs) represent such relationships, focusing on the domain of argument structure. We find that LLMs perform well in generalizing the distribution of a novel…

  PublisherOA PDFDOI

Recent grants

• NIH Grant R29DA004483

  NIH · $513k · 1992

• NIH Grant R01DA004483

  NIH · $464k · 1995

• Collaborative Research: Inductive Biases for the Acquisition of Syntactic Transformations in Neural Networks

  NSF · $343k · 2019–2025

Frequent coauthors

• Jungo Kasai

  Toyota Technological Institute at Chicago

  16 shared

• Owen Rambow

  15 shared

• Andrea Cometa

  IMT School for Advanced Studies Lucca

  13 shared

• Tal Linzen

  13 shared

• R. Thomas McCoy

  Princeton University

  11 shared

• Dan Friedman

  11 shared

• William Merrill

  11 shared

• Dragomir Radev

  10 shared

Labs

• Historical Linguistics and Australian Languages (HistLing)PI

Education

• PhD, Computer and Information Science

  University of Pennsylvania

  1992

• SB, Brain and Cognitive Science

  Massachusetts Institute of Technology

  1987

Similar researchers at Yale University

• Claire Bowernh-42
• Maria Piñangoh-25
• Veneeta Dayalh-25