On the Role of Low-Level Linguistic Tasks for Reading Time Prediction
| Autor: | Abdellah Fourtassi, Franck Dary, Alexis Nasr |
|---|---|
| Přispěvatelé: | Laboratoire d'Informatique et Systèmes (LIS), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS), Aix Marseille Université (AMU), Traitement Automatique du Langage Ecrit et Parlé (TALEP), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS), Dary, Franck |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Cognitive model
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI] Computer science media_common.quotation_subject [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing surprisal computer.software_genre [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] Reading (process) reading time media_common Parsing Lemmatisation Lexical analysis [SDV.NEU.SC]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Cognitive Sciences Cognition [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG] cognitive modeling Linguistics Comprehension [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing entropy computer Sentence [SDV.NEU.SC] Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Cognitive Sciences |
| Zdroj: | Proceedings of the Annual Meeting of the Cognitive Science Society, 43(43) 43rd Annual Meeting of the Cognitive Science Society 43rd Annual Meeting of the Cognitive Science Society, Jul 2021, Vienna, Austria. pp.452 |
| Popis: | International audience; It has been shown that complexity metrics, computed by a syntactic parser, is a predictor of human reading time, which is an approximation of human sentence comprehension difficulty. Nevertheless, parsers usually take as input sentences that have already been processed or even manually annotated. We propose to study a more realistic scenario, where the various processing levels (tokenization, PoS and morphology tagging, lemmatization, syntactic parsing and sentence segmentation) are predicted incrementally from raw text. To this end, we propose a versatile modeling framework, we call the Reading Machine, that performs all such linguistic tasks and allows to incorporate cognitive constrains such as incrementality. We illustrate the behavior of this setting through a case study where we test the hypothesis that the complexity metrics computed at different processing levels predicts human reading difficulty, and that when cognitive constraints are applied to the machine (e.g., incrementality), it yields better predictions. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|