The Acquisition of a Lexicon from Paired Phoneme Sequences and Semantic Representations
cmp-lg
2008-02-03 v1 Computation and Language
Abstract
We present an algorithm that acquires words (pairings of phonological forms and semantic representations) from larger utterances of unsegmented phoneme sequences and semantic representations. The algorithm maintains from utterance to utterance only a single coherent dictionary, and learns in the presence of homonymy, synonymy, and noise. Test results over a corpus of utterances generated from the Childes database of mother-child interactions are presented.
Keywords
Cite
@article{arxiv.cmp-lg/9407013,
title = {The Acquisition of a Lexicon from Paired Phoneme Sequences and Semantic Representations},
author = {Carl de Marcken},
journal= {arXiv preprint arXiv:cmp-lg/9407013},
year = {2008}
}
Comments
12 pages, postscript, to appear in ICGI '94