Differential Use of Implicit Negative Evidence in Generative and Discriminative Language Learning

Advances in Neural Information Processing Systems, Vol. 22, 2009

9 Pages Posted: 18 Apr 2011 Last revised: 20 Apr 2011

See all articles by Anne Showen Hsu

Anne Showen Hsu

University College London

Thomas E. Griffiths

University of California, Berkeley

Date Written: December 1, 2009

Abstract

A classic debate in cognitive science revolves around understanding how children learn complex linguistic rules, such as those governing restrictions on verb alternations, without negative evidence. Traditionally, formal learnability arguments have been used to claim that such learning is impossible without the aid of innate language-specific knowledge. However, recently, researchers have shown that statistical models are capable of learning complex rules from only positive evidence. These two kinds of learnability analyses differ in their assumptions about the distribution from which linguistic input is generated. The former analyses assume that learners seek to identify grammatical sentences in a way that is robust to the distribution from which the sentences are generated, analogous to discriminative approaches in machine learning. The latter assume that learners are trying to estimate a generative model, with sentences being sampled from that model. We show that these two learning approaches differ in their use of implicit negative evidence – the absence of a sentence – when learning verb alternations, and demonstrate that human learners can produce results consistent with the predictions of both approaches, depending on how the learning problem is presented.

Keywords: language acquisition, discriminative generative learning, verb alternation

Suggested Citation

Hsu, Anne Showen and Griffiths, Thomas E., Differential Use of Implicit Negative Evidence in Generative and Discriminative Language Learning (December 1, 2009). Advances in Neural Information Processing Systems, Vol. 22, 2009, Available at SSRN: https://ssrn.com/abstract=1810046

Anne Showen Hsu (Contact Author)

University College London ( email )

Gower Street
London, WC1E 6BT
United Kingdom

Thomas E. Griffiths

University of California, Berkeley ( email )

310 Barrows Hall
Berkeley, CA 94720
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
65
Abstract Views
666
Rank
617,745
PlumX Metrics