Full-text

URL: http://www-eksl.cs.umass.edu/papers/oates-cogsci99.ps

Cached: PDF-130K    PS-266K    PS.gz-61K

SAVE AS an easy-to-recall long filename:

Filename format: author--year--title   PDF-130K    PS-61K    :: About GZip'd PS

Filename format: author--year--title--journal|proceedings|...--pages   PDF-130K    PS-61K

Related links

CiteSeer: http://citeseer.ist.psu.edu/10879.html

Web search: Google Web Search   ::   Google Scholar

Within this site: Cited by (3)    References (12)

Paper at a Glance

Using Syntax to Learn Semantics: An Experiment
in Language Acquisition with a Mobile Robot
Tim Oates, Zachary Eyler­Walker and Paul R. Cohen
Computer Science Department, LGRC
University of Massachusetts, Box 34610
Amherst, MA 01003­4610
foates,zwalker,coheng@cs.umass.edu

Abstract Children learn natural languages by hearing utterances while interacting with their physical environment. We investigate one aspect of language acquisition by sim­ ilarly situated, embodied artificial agents ­ using in­ formation about syntax to learn linguistically relevant semantic features. The agent is assumed to have no innate knowledge of syntax, and instead leverages the weak information about syntax available in word co­ occurrences. Similarity of context (i.e. the surround­ ing words) is used to hierarchically cluster words, with clusters corresponding to sets of words that are similar syntactically and, often, semantically. The goal is to identify semantic features captured by the clusters. The leaves of the hierarchy are individual words, which are semantically very specific, and movement up the hier­ archy leads to less specificity. The results of an experi­ ment are discussed in which human subjects generated unrestricted natural language utterances to describe the activities of a Pioneer1 mobile robot. The combination of word clustering on this corpus and a common sub­ sequence algorithm applied to the time series of sensor values recorded by the robot made it possible for the Pioneer1 to learn a variety of semantic features.
Introduction Children learn a staggering number of semantic features that are relevant to their native language. For example, consider differences in the meanings of individual words, which can hinge on semantic features at various levels of detail. The meanings of push and shove are similar in that both involve contact between two entities and the application of force by one entity to the other. However, the meanings of these words differ in the ...

@techreport{oates99usingSyntax,
  author={Tim Oates and Zachary Eyler-Walker and Paul R. Cohen},
  title={Using Syntax to Learn Semantics: An Experiment in Language Acquisition with a Mobile Robot},
  year={1999},
  institution={Computer Science Department, University of Massachusetts at Amherst},
  note={Technical Report 99-35},
  url={http://www.isrl.uiuc.edu/~amag/langev/paper/oates99usingSyntax.html}
}

HOME   ::  Technical Report List   ::   Technical Report	Comments to: junwang4 you-know-at gmail.com	Last update: 4/1/09