Unsupervised Learning of Word Boundary with Description Length Gain

  • Chunyu Kityz, Yorick Wilksz
  • Published 1999


This paper presents an unsupervised approach to lexical acquisition with the goodness measure description length gain (DLG) formulated following classic information theory within the minimum description length (MDL) paradigm. The learning algorithm seeks for an optimal segmentation of an utterance that maximises the description length gain from the… (More)



Citations per Year

91 Citations

Semantic Scholar estimates that this publication has 91 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Kityz1999UnsupervisedLO, title={Unsupervised Learning of Word Boundary with Description Length Gain}, author={Chunyu Kityz and Yorick Wilksz}, year={1999} }