Macquarie University, Sydney Macquarie University ResearchOnline

Showing items 1 - 15 of 16.

Add to Quick Collection   All 16 Results

Sort:
 Add All Items to Quick Collection
Date: 2015
Language: eng
Resource Type: journal article
Identifier: http://hdl.handle.net/1959.14/356000
Description: A well-known effect in speech production is that more predictable linguistic constructions tend to be reduced. Recent work has interpreted this effect in an information-theoretic framework, proposing ... More
Reviewed: Reviewed
Date: 2014
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/1044108
Description: We present a new approach to inducing the syntactic categories of words, combining their distributional and morphological properties in a joint nonparametric Bayesian model based on the distance-depen ... More
Reviewed: Reviewed
Date: 2013
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/265207
Description: We summarize the accomplishments of a multi-disciplinary workshop exploring the computational and scientific issues surrounding zero resource (unsupervised) speech technologies and related models of e ... More
Reviewed: Reviewed
Date: 2013
Language: eng
Resource Type: journal article
Identifier: http://hdl.handle.net/1959.14/1105044
Description: This paper explores the use of Adaptor Grammars, a nonparametric Bayesian modelling framework, for minimally supervised morphological segmentation. We compare three training methods: unsupervised trai ... More
Reviewed: Reviewed
Date: 2013
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/286413
Description: Work on probabilistic models of natural language tends to focus on strings and trees, but there is increasing interest in more general graph-shaped structures since they seem to be better suited for r ... More
Reviewed: Reviewed
Date: 2013
Language: eng
Resource Type: journal article
Identifier: http://hdl.handle.net/1959.14/288279
Description: 12 page(s)
Reviewed: Reviewed
Date: 2012
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/216190
Description: Many semantic parsing models use tree transformations to map between natural language and meaning representation. However, while tree transformations are central to several state-of-the-art approaches ... More
Reviewed: Reviewed
Date: 2011
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/166662
Description: This paper introduces tree transducers as a unifying theory for semantic parsing models based on tree transformations. Many existing models use tree transformations, but implement specialized training ... More
Full Text: Full Text
Reviewed: Reviewed
Date: 2011
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/301576
Description: A well-known effect in speech production is that more predictable words tend to be phonetically reduced. Recent work has suggested that predictability effects result from hardwired properties of the l ... More
Reviewed: Reviewed
Date: 2011
Language: eng
Resource Type: journal article
Identifier: http://hdl.handle.net/1959.14/142427
Description: Standard statistical models of language fail to capture one of the most striking properties of natural languages: the power-law distribution in the frequencies of word tokens. We present a framework f ... More
Reviewed: Reviewed
Date: 2011
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/301577
Description: Learning to group words into phrases without supervision is a hard task for NLP systems, but infants routinely accomplish it. We hypothesize that infants use acoustic cues to prosody, which NLP system ... More
Reviewed: Reviewed
Date: 2009
Language: eng
Resource Type: journal article
Identifier: http://hdl.handle.net/1959.14/102227
Description: Since the experiments of Saffran et al. [Saffran, J., Aslin, R., & Newport, E. (1996). Statistical learning in 8-month-old infants. Science, 274, 1926–1928], there has been a great deal of interest in ... More
Reviewed: Reviewed
Date: 2009
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/156770
Description: The implementation of collapsed Gibbs samplers for non-parametric Bayesian models is non-trivial, requiring considerable book-keeping. Goldwater et al. (2006a) presented an approximation which signifi ... More
Reviewed: Reviewed
Date: 2009
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/323569
Description: One of the reasons nonparametric Bayesian inference is attracting attention in computational linguistics is because it provides a principled way of learning the units of generalization together with t ... More
Reviewed: Reviewed
Date: 2007
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/1162442
Description: 8 page(s)
Reviewed: Reviewed