Cross-Lingual Transfer of Cognitive Processing Complexity

Charlotte Pouw, Nora Hollenstein, Lisa Beinborn


Abstract
When humans read a text, their eye movements are influenced by the structural complexity of the input sentences. This cognitive phenomenon holds across languages and recent studies indicate that multilingual language models utilize structural similarities between languages to facilitate cross-lingual transfer. We use sentence-level eye-tracking patterns as a cognitive indicator for structural complexity and show that the multilingual model XLM-RoBERTa can successfully predict varied patterns for 13 typologically diverse languages, despite being fine-tuned only on English data. We quantify the sensitivity of the model to structural complexity and distinguish a range of complexity characteristics. Our results indicate that the model develops a meaningful bias towards sentence length but also integrates cross-lingual differences. We conduct a control experiment with randomized word order and find that the model seems to additionally capture more complex structural information.
Anthology ID:
2023.findings-eacl.49
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
655–669
Language:
URL:
https://aclanthology.org/2023.findings-eacl.49
DOI:
10.18653/v1/2023.findings-eacl.49
Bibkey:
Cite (ACL):
Charlotte Pouw, Nora Hollenstein, and Lisa Beinborn. 2023. Cross-Lingual Transfer of Cognitive Processing Complexity. In Findings of the Association for Computational Linguistics: EACL 2023, pages 655–669, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Cross-Lingual Transfer of Cognitive Processing Complexity (Pouw et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-eacl.49.pdf
Software:
 2023.findings-eacl.49.software.zip
Video:
 https://aclanthology.org/2023.findings-eacl.49.mp4