Abstract
While the use of character models has been popular in NLP applications, it has not been explored much in the context of psycholinguistic modeling. This paper presents a character model that can be applied to a structural parser-based processing model to calculate word generation probabilities. Experimental results show that surprisal estimates from a structural processing model using this character model deliver substantially better fits to self-paced reading, eye-tracking, and fMRI data than those from large-scale language models trained on much more data. This may suggest that the proposed processing model provides a more humanlike account of sentence processing, which assumes a larger role of morphology, phonotactics, and orthographic complexity than was previously thought.- Anthology ID:
- 2021.acl-long.290
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3746–3757
- Language:
- URL:
- https://aclanthology.org/2021.acl-long.290
- DOI:
- 10.18653/v1/2021.acl-long.290
- Cite (ACL):
- Byung-Doh Oh, Christian Clark, and William Schuler. 2021. Surprisal Estimators for Human Reading Times Need Character Models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3746–3757, Online. Association for Computational Linguistics.
- Cite (Informal):
- Surprisal Estimators for Human Reading Times Need Character Models (Oh et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2021.acl-long.290.pdf
- Code
- byungdoh/acl21_semproc
- Data
- Natural Stories, Penn Treebank