@inproceedings{zaitova-etal-2024-cross,
title = {Cross-Linguistic Processing of Non-Compositional Expressions in Slavic Languages},
author = {Iuliia Zaitova and Irina Stenger and Tania Avgustinova},
editor = {Michael Zock and Emmanuele Chersoni and Yu-Yin Hsu and Simon de Deyne},
url = {https://aclanthology.org/2024.cogalex-1.10/},
year = {2024},
date = {2024},
booktitle = {Proceedings of the Workshop on Cognitive Aspects of the Lexicon @ LREC-COLING 2024},
pages = {86-97},
publisher = {ELRA and ICCL},
address = {Torino, Italia},
abstract = {This study focuses on evaluating and predicting the intelligibility of non-compositional expressions within the context of five closely related Slavic languages: Belarusian, Bulgarian, Czech, Polish, and Ukrainian, as perceived by native speakers of Russian. Our investigation employs a web-based experiment where native Russian respondents take part in free-response and multiple-choice translation tasks. Based on the previous studies in mutual intelligibility and non-compositionality, we propose two predictive factors for reading comprehension of unknown but closely related languages: 1) linguistic distances, which include orthographic and phonological distances; 2) surprisal scores obtained from monolingual Language Models (LMs). Our primary objective is to explore the relationship of these two factors with the intelligibility scores and response times of our web-based experiment. Our findings reveal that, while intelligibility scores from the experimental tasks exhibit a stronger correlation with phonological distances, LM surprisal scores appear to be better predictors of the time participants invest in completing the translation tasks.},
pubstate = {published},
type = {inproceedings}
}