Linguistic Structure as Composition and Perturbation
cmp-lg
2008-02-03 v1 Computation and Language
Abstract
This paper discusses the problem of learning language from unprocessed text and speech signals, concentrating on the problem of learning a lexicon. In particular, it argues for a representation of language in which linguistic parameters like words are built by perturbing a composition of existing parameters. The power of this representation is demonstrated by several examples in text segmentation and compression, acquisition of a lexicon from raw speech, and the acquisition of mappings between text and artificial representations of meaning.
Keywords
Cite
@article{arxiv.cmp-lg/9606027,
title = {Linguistic Structure as Composition and Perturbation},
author = {Carl de Marcken},
journal= {arXiv preprint arXiv:cmp-lg/9606027},
year = {2008}
}
Comments
7 pages