An explicit statistical model of learning lexical segmentation using multiple cues

This paper presents an unsupervised and incremental model of learning segmenta-tion that combines multiple cues whose use by children and adults were attested by experimental studies. The cues we exploit in this study are predictability statistics, phonotactics, lexical stress and partial lex-ical information. The performance of the model presented in this paper is competi-tive with the state-of-the-art segmentation models in the literature, while following the child language acquisition more faith-fully. Besides the performance improve-ments over the similar models in the liter-ature, the cues are combined in an explicit manner, allowing easier interpretation of what the model learns.