Sign constraints on feature weights improve a joint model of word segmentation and phonology

@inproceedings{Johnson2015SignCO,
  title={Sign constraints on feature weights improve a joint model of word segmentation and phonology},
  author={Mark Johnson and Joe Pater and Robert Staubs and Emmanuel Dupoux},
  booktitle={HLT-NAACL},
  year={2015}
}
This paper describes a joint model of word segmentation and phonological alternations, which takes unsegmented utterances as input and infers word segmentations and underlying phonological representations. The model is a Maximum Entropy or log-linear model, which can express a probabilistic version of Opti- mality Theory (OT; Prince and Smolensky (2004)), a standard phonological framework. The features in our model are inspired by OT's Markedness and Faithfulness constraints. Fol- lowing the OT… CONTINUE READING

Topics from this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 28 REFERENCES

Buckeye corpus of conversational speech

Mark A. Pitt, Laura Dilley, +4 authors Eric Fosler-Lussier
  • 2007
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Exploring the Role of Stress in Bayesian Word Segmentation using Adaptor Grammars

  • Transactions of the Association for Computational Linguistics
  • 2014
VIEW 1 EXCERPT