|
Large language models and human language processing: from variability to prediction| title | Large language models and human language processing: from variability to prediction |
|---|
| start_date | 2024/01/17 |
|---|
| schedule | 17h-18h |
|---|
| online | no |
|---|
| location_info | via Zoom |
|---|
| summary | Current language models have been shown to simulate human language surprisingly well, generating fluent, grammatical text and encoding meaning representations that resemble human semantic knowledge. Can known properties of human language use provide valuable insights for language models? And conversely, can language modelling techniques contribute to our understanding of human language processing? In this talk, I will start by arguing that to be considered good statistical models of language production, language models should entertain levels of uncertainty calibrated to the degree of variability observed in humans, and show that to a large extent they do, albeit with some caveats. Building on this result, I will then propose a novel measure to quantify the predictability of an utterance using neural text generators and show that it correlates with reading times and acceptability judgements remarkably well, complementing classic measures of surprisal. |
|---|
| responsibles | Bernard |
|---|
Workflow history| from state (1) | to state | comment | date |
|---|
| submitted | published | | 2023/11/09 14:39 UTC |
| |
|