Towards an Automated Model of Comprehension (AMoC)

• Published in: Lifelong Technology-Enhanced Learning pp. 427 - 436
• Main Authors: Dascalu, Mihai, Paraschiv, Ionut Cristian, McNamara, Danielle S., Trausan-Matu, Stefan
• Format: Book Chapter
• Language: English
• Published: Cham Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Comprehension modeling; Landscape Model; Natural Language Processing; Semantic models
• ISBN: 331998571X; 9783319985718
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-98572-5_33

Reading is a complex cognitive process wherein learners acquire new information and consolidate their knowledge. Readers create a mental representation for a given text by processing relevant words that, along with prior inferred concepts, become activated and establish meaningful associations. Our automated model of comprehension (AMoC) uses an automated approach for simulating the ways in which learners read and conceptualize by considering both text-based information consisting of syntactic dependencies, as well as inferred concepts from semantic models. AMoC makes use of cutting edge Natural Language Processing techniques, transcends beyond existing models, and represents a novel alternative for modeling how learners potentially conceptualize read information. This study presents side-by-side comparisons of the results generated by our model versus the ones generated by the Landscape model.