110 citations · 236 across the 25 of their papers we have counts for
8 papers · 1 filter
Language model acceptability judgements are not always robust to context
Koustuv Sinha, Jon Gauthier, Aaron Mueller +4
Targeted syntactic evaluations of language models ask whether models show stable preferences for syntactically acceptable content over minimal-pair unacceptable inputs. Most target…
Probing for Incremental Parse States in Autoregressive Language Models
Tiwalayo Eisape, Vineet Gangireddy, Roger P. Levy +1
Next-word predictions from autoregressive neural language models show remarkable sensitivity to syntax. This work evaluates the extent to which this behavior arises as a result of…
On the Effect of Anticipation on Reading Times
Tiago Pimentel, Clara Meister, Ethan G. Wilcox +2
Over the past two decades, numerous studies have demonstrated how less predictable (i.e., higher surprisal) words take more time to read. In general, these studies have implicitly…
Towards Human-Agent Communication via the Information Bottleneck Principle
Mycal Tucker, Julie Shah, Roger Levy +1
Emergent communication research often focuses on optimizing task-specific utility as a driver for communication. However, human languages appear to evolve under pressure to efficie…
How Adults Understand What Young Children Say
Stephan C. Meylan, Ruthe Foushee, Nicole H. Wong +2
Children's early speech often bears little resemblance to that of adults, and yet parents and other caregivers are able to interpret that speech and react accordingly. Here we inve…
When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes
Mycal Tucker, Tiwalayo Eisape, Peng Qian +2
Recent causal probing literature reveals when language models and syntactic probes use similar representations. Such techniques may yield "false negative" causality results: models…
Analyzing Wrap-Up Effects through an Information-Theoretic Lens
Clara Meister, Tiago Pimentel, Thomas Hikaru Clark +2
Numerous analyses of reading time (RT) data have been implemented -- all in an effort to better understand the cognitive processes driving reading comprehension. However, data meas…
Grammar-Based Grounded Lexicon Learning
Jiayuan Mao, Haoyue Shi, Jiajun Wu +2
We present Grammar-Based Grounded Lexicon Learning (G2L2), a lexicalist approach toward learning a compositional and grounded meaning representation of language from grounded data,…