Is deeper always better? Replacing linear mappings with deep learning networks in the Discriminative Lexicon Model.
Abstract
. Applied to average reaction times, we find that DDL is outperformed by frequency-informed linear mappings (FIL). However, DDL trained in a frequency-informed way ("frequency-informed" deep learning; FIDDL) substantially outperforms FIL. Finally, while linear mappings can very effectively be updated from trial-to-trial to model incremental lexical learning, deep mappings cannot do so as effectively. At present, both linear and deep mappings are informative for understanding language.
Fields of Study & Subjects
Neurobiology of Language and Bilingualism
Topic Modeling
Natural Language Processing Techniques
Publication details
- Journal / source
- PubMed
- Publisher
- Walter de Gruyter GmbH
- Volume
- 12
- Issue
- Suppl1
- Pages
- 11–25
- Publication date
- 1 May 2026
- Language
- EN