Material Detail

A Bayesian approach to Word Segmentation: Theoretical and Experimental results

A Bayesian approach to Word Segmentation: Theoretical and Experimental results

This video was recorded at Workshop on Machine Learning and Cognitive Science of Language Acquisition, London 2007. Word segmentation. One of the first problems infants must solve when learning language. Infants make use of many different cues - phonotactics, allophonic variation, metrical (stress) patterns, effects of coarticulation, and statistical regularities in syllable sequences. Statistics may provide initial bootstrapping - used very early (Thiessen & Saffran, 2003); language-independent.

Quality

  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.