An Efficient, Probabilistically Sound Algorithm for Segmentation and Word Discovery

TL;DR

This paper introduces a probabilistically sound, language-independent algorithm for segmenting text into words without supervision, based on a flexible model that considers the entire corpus as a single probabilistic event.

Contribution

It presents a novel, modular, probabilistic model for unsupervised word boundary detection that outperforms previous algorithms in specific speech segmentation tasks.

Findings

More effective than existing algorithms when boundaries are given

Performs well on short utterances in spontaneous speech

Uses a language-independent, corpus-wide probability model

Abstract

This paper presents a model-based, unsupervised algorithm for recovering word boundaries in a natural-language text from which they have been deleted. The algorithm is derived from a probability model of the source that generated the text. The fundamental structure of the model is specified abstractly so that the detailed component models of phonology, word-order, and word frequency can be replaced in a modular fashion. The model yields a language-independent, prior probability distribution on all possible sequences of all possible words over a given alphabet, based on the assumption that the input was generated by concatenating words from a fixed but unknown lexicon. The model is unusual in that it treats the generation of a complete corpus, regardless of length, as a single event in the probability space. Accordingly, the algorithm does not estimate a probability distribution on words; instead, it attempts to calculate the prior probabilities of various word sequences that could underlie the observed text. Experiments on phonemic transcripts of spontaneous speech by parents to young children suggest that this algorithm is more effective than other proposed algorithms, at least when utterance boundaries are given and the text includes a substantial number of short utterances. Keywords: Bayesian grammar induction, probability models, minimum description length (MDL), unsupervised learning, cognitive modeling, language acquisition, segmentation