Complexity Issues in Robotic Machine Learning of Natural Language

Suppes, Patrick; Liang, Lin; Böttner, Michale

doi:10.1007/978-1-4613-9229-3_4

Cited by 6 publications

(7 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The process of modelling child language acquisi tion is very complex, as many of the first at tempts confirmed (Feldman et al, 1990;Suppes, Liang & Bottner, 1991). Rather than modelling the process in entirety, an undoubtedly daunting task, modellers took the simplified approach of focusing upon individual linguistic behaviours, leading to much research into relatively con strained problems such as understanding over and undergeneralisation errors (Plunkett, Sinha, Moller & Strandsby, 1992), single word learning (Regier, 2005), syntactic category acquisition (Redington, Chater & Finch, 1988) and past tense learning (Rumelhart & Mcclelland, 1986).…”

Section: Introductionmentioning

confidence: 99%

A collaborative tool for the computational modelling of child language acquisition

Jack

2009

Proceedings of the EACL 2009 Workshop on Cognitive Aspects of Computational Language Acquisition - CACLA '09

View full text Add to dashboard Cite

A large number of computational language learners have been proposed for modelling the process of child language acquisition. Com paring them, however, can be difficult due to the different assumptions that they make, the diverse test results presented, and the different linguistic behaviours investigated. This paper introduces a toolkit that allows different lan guage learners to be trained, tested and ana lysed under standardised conditions. The res ults can be easily compared with one another and with typical child language development to highlight the relative advantages and disad vantages of learners.

show abstract

Section: Introductionmentioning

confidence: 99%

A collaborative tool for the computational modelling of child language acquisition

Jack

2009

Proceedings of the EACL 2009 Workshop on Cognitive Aspects of Computational Language Acquisition - CACLA '09

View full text Add to dashboard Cite

show abstract

“…The details of the learning curves that are generated from our procedure of machine learning are as described in the axioms but will not be analyzed here, because we already have a very thorough discussion of learning curves in our earlier paper (Suppes, Liang, & Bottner, 1992). We also do not analyze here in detail the learning of denotational value as characterized in Axiom 2.3.…”

Section: Grammars Generatedmentioning

confidence: 99%

“…*The results reported were originally presented at the Eighth Amsterdam Colloquium, December 17-20,1991. Our axioms, given in Section 2, for machine learning of comprehension are long and complicated, even though we analyze here the learning of relatively small fragments of the natural languages considered, but they do faithfully reflect the computer implementation, as well as extend the axioms given in our earlier paper (Suppes, Liang, & Bottner, 1992). We do believe the learning principles expressed in the axioms can serve as the basis for learning much more extended fragments and represent concepts that must be present in any system that starts with no knowledge of the natural language to be learned.…”

Section: Introduction and Overviewmentioning

confidence: 99%

Untitled

1995

Self Cite

View full text Add to dashboard Cite

Abstract. We are developing a theory of probabilistic language learning in the context of robotic instruction in elementary assembly actions. We describe the process of machine learning in terms of the various events that happen on a given trial, including the crucial association of words with internal representations of their meaning. Of central importance in learning is the generalization from utterances to grammatical forms. Our system derives a comprehension grammar for a superset of a natural language from pairs of verbal stimuli like Go to the screw! and corresponding internal representations of coerced actions. For the derivation of a grammar no knowledge of the language to be learned is assumed but only knowledge of an internal language.We present grammars for English, Chinese, and German generated from a finite sample of about 500 commands that are roughly equivalent across the three languages. All of the three grammars, which are context-free in form, accept an infinite set of commands in the given language.

show abstract

“…The details of the learning curves that are generated from our procedure of machine learning are as described in the axioms but will not be analyzed here, because we already have a very thorough discussion of learning curves in our earlier paper (Suppes, Liang, & Böttner, 1992). We also do not analyze here in detail the learning of denotational value as characterized in Axiom 2.3.…”

Section: Grammars Generatedmentioning

confidence: 99%

“…Our axioms, given in Section 2, for machine learning of comprehension are long and complicated, even though we analyze here the learning of relatively small fragments of the natural languages considered, but they do faithfully reflect the computer implementation, as weil as extend the axioms given in our earlier paper (Suppes, Liang, & Böttner, 1992). We do believe the learning principles expressed in the axioms can serve as the basis for learning much more extended fragments and represent concepts that taust be present in any system that starts with no knowledge of the natural language to be learned.…”

Section: Introduction and Overviewmentioning

confidence: 99%

Comprehension grammars generated from machine learning of natural languages

Suppes¹,

B�ttner²,

Liang³

1995

Mach Learn

Self Cite

View full text Add to dashboard Cite

Abstract.We are developing a theory of probabilistic language leaming in the context of robotic instruction in elementary assembly actions. We describe the process of machine learning in terms of the various events that happen on a given trial, including the crucial association of words with intemal representations of their meaning. Of central importance in learning is the generalization from utterances to grammatical forms. Our system derives a comprehension grammar for a superset of a natural language from pairs of verbal stimuli like Go to the screw! and corresponding internal representations of coerced actions. For the derivation of a grammar no knowledge of the language to be learned is assumed but only knowledge of an internal language.We present grammars for English, Chinese, and German generated from a finite sample of about 500 commands that are roughly equivalent across the three languages. All of the three grammars, which are context-free in form, accept an infinite set of commands in the given language.

show abstract

Complexity Issues in Robotic Machine Learning of Natural Language

Cited by 6 publications

References 3 publications

A collaborative tool for the computational modelling of child language acquisition

A collaborative tool for the computational modelling of child language acquisition

Untitled

Comprehension grammars generated from machine learning of natural languages

Contact Info

Product

Resources

About