@inproceedings{alves-etal-2026-cognitive,
title = {Cognitive Signatures of Multi-Word Expressions: Reading-Time and Surprisal},
author = {Diego Alves and Sergei Bagdasarov and Elke Teich},
editor = {Atul Kr. Ojha and Verginica Barbu Mititelu and Mathieu Constant and Ivelina Stoyanova and A. Seza Doğru{\"o}z and Alexandre Rademaker},
url = {https://aclanthology.org/2026.mwe-1.5/},
doi = {https://doi.org/10.18653/v1/2026.mwe-1.5},
year = {2026},
date = {2026},
booktitle = {Proceedings of the 22nd Workshop on Multiword Expressions (MWE 2026)},
isbn = {979-8-89176-363-0},
pages = {48-53},
publisher = {Association for Computational Linguistics},
address = {Rabat, Marocco},
abstract = {This study investigates whether eye-tracking measures predict if a word is the final token of a multi-word expression (MWE), focusing on two understudied MWE types: fixed expressions (e.g., <i>due to</i>) and phrasal verbs (e.g., <i>turn out</i>). Using mixed-effects logistic regression, we compared tokens in MWE contexts with the same tokens in non-MWE contexts. Results reveal a clear difference in processing. For fixed expressions, reading-time measures significantly predict MWEhood. In contrast, phrasal verbs show no consistent predictive effects. Additionally, we compared the reading-time models to models that included GPT-2 surprisal as a predictor. While surprisal does predict MWEhood, it fails to capture the distinction between types. These findings highlight the need to consider MWE typology in models of formulaic language processing.
<dl></dl>},
pubstate = {published},
type = {inproceedings}
}