Children can acquire language from less than 100 million words of input. Large language models are far less data-efficient: they typically require 3 or 4 orders of magnitude more data …
Recurrent neural network grammars (RNNGs) are generative models of (tree, string) pairs that rely on neural networks to evaluate derivational choices. Parsing with them using beam …
More predictable words are easier to process—they are read faster and elicit smaller neural signals associated with processing difficulty, most notably, the N400 component of the event …
We analyze if large language models are able to predict patterns of human reading behavior. We compare the performance of language-specific and multilingual pretrained …
Long document coreference resolution remains a challenging task due to the large memory and runtime requirements of current models. Recent work doing incremental coreference …
We investigate the extent to which word surprisal can be used to predict a neural measure of human language processing difficulty-the N400. To do this, we use recurrent neural …
Despite being designed for performance rather than cognitive plausibility, transformer language models have been found to be better at predicting metrics used to assess human …
Psycholinguistic research shows that key properties of the human sentence processor are incrementality, connectedness (partial structures contain no unattached nodes), and …
Incremental processing allows interactive systems to respond based on partial inputs, which is a desirable property eg in dialogue agents. The currently popular Transformer architecture …