Linguistic Structure as Composition and Perturbation

TL;DR

This paper proposes a novel linguistic representation framework where words are formed by perturbing compositions of existing parameters, demonstrated through applications in segmentation, compression, and lexicon acquisition from raw speech.

Contribution

It introduces a new approach to language learning based on perturbation of composed parameters, advancing methods for lexicon acquisition and text-speech mapping.

Findings

Effective in text segmentation and compression

Successful in acquiring lexicons from raw speech

Demonstrates mappings between text and artificial meaning representations

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.