Which distributional cues help the most? Unsupervised context selection for lexical category acquisition

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

*Corresponding author for this work

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

Abstract

Starting from the distributional bootstrapping hypothesis, we propose an unsupervised model that selects the most useful distributional information according to its salience in the input, incorporating psycholinguistic evidence. With a supervised Parts-of-Speech tagging experiment, we provide preliminary results suggesting that the distributional contexts extracted by our model yield similar performances as compared to current approaches from the literature, with a gain in psychological plausibility. We also introduce a more principled way to evaluate the effectiveness of distributional contexts in helping learners to group words in syntactic categories.
Original languageEnglish
Title of host publicationProceedings of the 6th Workshop on Cognitive Aspects of Computational Language Learning (CogACLL)
PublisherAssociation for Computational Linguistics (ACL)
Pages33-39
Number of pages7
Publication statusPublished - Sep 2015
Externally publishedYes

Fingerprint Dive into the research topics of 'Which distributional cues help the most? Unsupervised context selection for lexical category acquisition'. Together they form a unique fingerprint.

Cite this