Towards a model of prediction-based syntactic category acquisition: first steps with word embeddings

Robert Grimm*, Giovanni Cassani, Walter Daelemans, Steven Gillis

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

We present a prototype model, based on a combination of count-based distributional semantics and prediction-based neural word embeddings, which learns about syntactic categories as a function of (1) writing contextual, phonological, and lexical-stress-related information to memory and (2) predicting upcoming context words based on memorized information. The system is a first step towards utilizing recently popular methods from Natural Language Processing for exploring the role of prediction in childrens acquisition of syntactic categories.
Original languageEnglish
Title of host publicationProceedings of the 6th Workshop on Cognitive Aspects of Computational Language Learning
PublisherAssociation for Computational Linguistics (ACL)
Pages28-32
Number of pages5
Publication statusPublished - Sep 2015
Externally publishedYes

Fingerprint Dive into the research topics of 'Towards a model of prediction-based syntactic category acquisition: first steps with word embeddings'. Together they form a unique fingerprint.

  • Cite this

    Grimm, R., Cassani, G., Daelemans, W., & Gillis, S. (2015). Towards a model of prediction-based syntactic category acquisition: first steps with word embeddings. In Proceedings of the 6th Workshop on Cognitive Aspects of Computational Language Learning (pp. 28-32). Association for Computational Linguistics (ACL).