Shammur Absar Chowdhury and Roberto Zamparelli
COLING, 2018
Publication year: 2018

Abstract

The paper explores the ability of LSTM networks trained on a language modeling task to detect linguistic structures which are ungrammatical due to extraction violations (extra arguments and subject-relative clause island violations), and considers its implications for the debate on language innatism. The results show that the current RNN model can correctly classify (un)grammatical sentences, in certain conditions, but it is sensitive to linguistic processing factors and probably ultimately unable to induce a more abstract notion of grammaticality, at least in the domain we tested.

Leave a Reply

Your email address will not be published. Required fields are marked *

fourteen + 20 =