Corpus linguistics and naive discriminative learning
R. Baayen. Revista Brasileira de Linguística Aplicada, (00 2011)
Abstract
Three classifiers from machine learning (the generalized linear mixed model, memory based learning, and support vector machines) are compared with a naive discriminative learning classifier, derived from basic principles of error-driven learning characterizing animal and human learning. Tested on the dative alternation in English, using the Switchboard data from (BRESNAN; CUENI; NIKITINA; BAAYEN, 2007), naive discriminative learning emerges with stateof-the-art predictive accuracy. Naive discriminative learning offers a united framework for understanding the learning of probabilistic distributional patterns, for classification, and for a cognitive grounding of distinctive collexeme analysis.
Description
Corpus linguistics and naive discriminative learning
%0 Journal Article
%1 baayen2011corpus
%A Baayen, R. Harald
%D 2011
%I scielo
%J Revista Brasileira de Linguística Aplicada
%K Switchboard; alternation; analysis. collexeme dative distributional frecuency, learning; machine, n-gram, patterns; probabilistic
%P 295 - 328
%T Corpus linguistics and naive discriminative learning
%U http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1984-63982011000200003&nrm=iso
%V 11
%X Three classifiers from machine learning (the generalized linear mixed model, memory based learning, and support vector machines) are compared with a naive discriminative learning classifier, derived from basic principles of error-driven learning characterizing animal and human learning. Tested on the dative alternation in English, using the Switchboard data from (BRESNAN; CUENI; NIKITINA; BAAYEN, 2007), naive discriminative learning emerges with stateof-the-art predictive accuracy. Naive discriminative learning offers a united framework for understanding the learning of probabilistic distributional patterns, for classification, and for a cognitive grounding of distinctive collexeme analysis.
@article{baayen2011corpus,
abstract = {Three classifiers from machine learning (the generalized linear mixed model, memory based learning, and support vector machines) are compared with a naive discriminative learning classifier, derived from basic principles of error-driven learning characterizing animal and human learning. Tested on the dative alternation in English, using the Switchboard data from (BRESNAN; CUENI; NIKITINA; BAAYEN, 2007), naive discriminative learning emerges with stateof-the-art predictive accuracy. Naive discriminative learning offers a united framework for understanding the learning of probabilistic distributional patterns, for classification, and for a cognitive grounding of distinctive collexeme analysis.},
added-at = {2016-10-26T23:44:37.000+0200},
author = {Baayen, R. Harald},
biburl = {https://www.bibsonomy.org/bibtex/2592e1d85cdf6d5258aa03a13de75008e/mauroscout},
crossref = {10.1590/S1984-63982011000200003},
description = {Corpus linguistics and naive discriminative learning},
interhash = {9ba732bf825d2f23953199ab38ad7338},
intrahash = {592e1d85cdf6d5258aa03a13de75008e},
issn = {1984-6398},
journal = {{Revista Brasileira de Linguística Aplicada}},
keywords = {Switchboard; alternation; analysis. collexeme dative distributional frecuency, learning; machine, n-gram, patterns; probabilistic},
language = {en},
month = {00},
pages = {295 - 328},
publisher = {scielo},
timestamp = {2016-10-29T12:55:16.000+0200},
title = {{Corpus linguistics and naive discriminative learning}},
url = {http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1984-63982011000200003&nrm=iso},
volume = 11,
year = 2011
}