Exploiting Social Information in Grounded Language Learning via Grammatical Reduction
Article Structure
Abstract
This paper uses an unsupervised model of grounded language acquisition to study the role that social cues play in language acquisition.
Introduction
From learning sounds to learning the meanings of words, social interactions are extremely important for children’s early language acquisition (Baldwin, 1993; Kuhl et al., 2003).
Topics
unigram
Appears in 14 sentences as: Unigram (1) unigram (13)
In Exploiting Social Information in Grounded Language Learning via Grammatical Reduction
- We show how to model the task of inferring which objects are being talked about (and which words refer to which objects) as standard grammatical inference, and describe PCFG-based unigram models and adaptor grammar-based collocation models for the task.Page 1, “Abstract”
- The unigram model we describe below corresponds most closely to the FrankPage 2, “Introduction”
- 2.1 Topic models and the unigram PCFGPage 4, “Introduction”
- This leads to our first model, the unigram grammar, which is a PCFG.1Page 4, “Introduction”
- 1In fact, the unigram grammar is equivalent to a HMM, but the PCFG parameterisation makes clear the relationshipPage 4, “Introduction”
- gure 4: The rule schema that generate the unigram ZFG.Page 4, “Introduction”
- Figure 4 presents the rules of the unigram gram-.ar.Page 4, “Introduction”
- The rules expanding the Topic, nonterminals are exactly as in unigram PCFG.Page 5, “Introduction”
- The prefix (not shown here) is parsed exactly as in the Unigram PCFG.Page 5, “Introduction”
- Here we explore a simple “collocation” extension to the unigram PCFG which associates multiword collocations, rather than individual words, with topics.Page 5, “Introduction”
- Each collocation is either associated with the sentence topic or with the None topic, just like words in the unigram model.Page 5, “Introduction”
See all papers in Proc. ACL 2012 that mention unigram.
See all papers in Proc. ACL that mention unigram.
Back to top.
language acquisition
Appears in 7 sentences as: language acquisition (9)
In Exploiting Social Information in Grounded Language Learning via Grammatical Reduction
- This paper uses an unsupervised model of grounded language acquisition to study the role that social cues play in language acquisition .Page 1, “Abstract”
- From learning sounds to learning the meanings of words, social interactions are extremely important for children’s early language acquisition (Baldwin, 1993; Kuhl et al., 2003).Page 1, “Introduction”
- In order to study the role that social cues play in language acquisition , this paper presents a structured statistical model ofPage 1, “Introduction”
- Thus, this work is consistent with a view of language acquisition in which children learn to learn, discovering organizing principles for how language is organized and used socially (Baldwin, 1993; Hollich et al., 2000; Smith et al., 2002).Page 1, “Introduction”
- Adaptor grammars are a framework for specifying hierarchical nonparametric models that has been previously used to model language acquisition (Johnson, 2008).Page 1, “Introduction”
- There is a growing body of work on the role of social cues in language acquisition .Page 2, “Introduction”
- The language acquisition research community has long recognized the importance of social cues for child language acquisition (Baldwin, 1991; Carpenter et al., 1998; Kuhl et al., 2003).Page 2, “Introduction”
See all papers in Proc. ACL 2012 that mention language acquisition.
See all papers in Proc. ACL that mention language acquisition.
Back to top.
topic models
Appears in 4 sentences as: topic model (1) Topic models (1) topic models (2)
In Exploiting Social Information in Grounded Language Learning via Grammatical Reduction
- (This is also appropriate, given that our models are specialisations of topic models ).Page 2, “Introduction”
- 2.1 Topic models and the unigram PCFGPage 4, “Introduction”
- (2010) observe, this kind of grounded learning can be viewed as a specialised kind of topic inference in a topic model , where the utterance topic is constrained by the available objects (possible topics).Page 4, “Introduction”
- We exploit this observation here using a reduction based on the reduction of LDA topic models to PCFGs proposed by Johnson (2010).Page 4, “Introduction”
See all papers in Proc. ACL 2012 that mention topic models.
See all papers in Proc. ACL that mention topic models.
Back to top.
