Collateral facilitation in humans and language models
This work addresses the problem of understanding cognitive and computational language processing for researchers in psycholinguistics and AI, though it is incremental as it extends known human phenomena to models.
The study investigated whether human and language model predictions are similarly influenced by semantic context, finding that both humans and eight transformer models show a processing advantage for highly anomalous words when they are semantically related to the context.
Are the predictions of humans and language models affected by similar things? Research suggests that while comprehending language, humans make predictions about upcoming words, with more predictable words being processed more easily. However, evidence also shows that humans display a similar processing advantage for highly anomalous words when these words are semantically related to the preceding context or to the most probable continuation. Using stimuli from 3 psycholinguistic experiments, we find that this is also almost always also the case for 8 contemporary transformer language models (BERT, ALBERT, RoBERTa, XLM-R, GPT-2, GPT-Neo, GPT-J, and XGLM). We then discuss the implications of this phenomenon for our understanding of both human language comprehension and the predictions made by language models.