Generalized Measures of Anticipation and Responsivity in Online Language Processing

Mario Giulianelli, Andreas Opedal, Ryan Cotterell


Abstract
We introduce a generalization of classic information-theoretic measures of predictive uncertainty in online language processing, based on the simulation of expected continuations of incremental linguistic contexts. Our framework provides a formal definition of anticipatory and responsive measures, and it equips experimenters with the tools to define new, more expressive measures beyond standard next-symbol entropy and surprisal. While extracting these standard quantities from language models is convenient, we demonstrate that using Monte Carlo simulation to estimate alternative responsive and anticipatory measures pays off empirically: New special cases of our generalized formula exhibit enhanced predictive power compared to surprisal for human cloze completion probability as well as ELAN, LAN, and N400 amplitudes, and greater complementarity with surprisal in predicting reading times.
Anthology ID:
2024.findings-emnlp.682
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11648–11669
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.682/
DOI:
10.18653/v1/2024.findings-emnlp.682
Bibkey:
Cite (ACL):
Mario Giulianelli, Andreas Opedal, and Ryan Cotterell. 2024. Generalized Measures of Anticipation and Responsivity in Online Language Processing. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11648–11669, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Generalized Measures of Anticipation and Responsivity in Online Language Processing (Giulianelli et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.682.pdf