125 citations · 584 across the 45 of their papers we have counts for
9 papers · 1 filter
RNNs Implicitly Implement Tensor Product Representations
R. Thomas McCoy, Tal Linzen, Ewan Dunbar +1
Recurrent neural networks (RNNs) can learn continuous vector representations of symbolic structures such as sequences and sentences; these representations often exhibit linear regu…
Non-entailed subsequences as a challenge for natural language inference
R. Thomas McCoy, Tal Linzen
Neural network models have shown great success at natural language inference (NLI), the task of determining whether a premise entails a hypothesis. However, recent studies suggest…
Can Entropy Explain Successor Surprisal Effects in Reading?
Marten van Schijndel, Tal Linzen
Human reading behavior is sensitive to surprisal: more predictable words tend to be read faster. Unexpectedly, this applies not only to the surprisal of the word that is currently…
What can linguistics and deep learning contribute to each other?
Tal Linzen
Joe Pater's target article calls for greater interaction between neural network research and linguistics. I expand on this call and show how such interaction can benefit both field…
Targeted Syntactic Evaluation of Language Models
Rebecca Marvin, Tal Linzen
We present a dataset for evaluating the grammaticality of the predictions of a language model. We automatically construct a large number of minimally different pairs of English sen…
A Neural Model of Adaptation in Reading
Marten van Schijndel, Tal Linzen
It has been argued that humans rapidly adapt their lexical and syntactic expectations to match the statistics of the current linguistic context. We provide further support to this…
Distinct patterns of syntactic agreement errors in recurrent networks and humans
Tal Linzen, Brian Leonard
Determining the correct form of a verb in context requires an understanding of the syntactic structure of the sentence. Recurrent neural networks have been shown to perform this ta…
Colorless green recurrent networks dream hierarchically
Kristina Gulordava, Piotr Bojanowski, Edouard Grave +2
Recurrent neural networks (RNNs) have achieved impressive results in a variety of linguistic processing tasks, suggesting that they can induce non-trivial properties of language. W…
Revisiting the poverty of the stimulus: hierarchical generalization without a hierarchical bias in recurrent neural networks
R. Thomas McCoy, Robert Frank, Tal Linzen
Syntactic rules in natural language typically need to make reference to hierarchical sentence structure. However, the simple examples that language learners receive are often equal…