ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

Recent results in automatic learning rules for semantic interpretation

Roland Kuhn, Renato De Mori

This article describes a new method for building a natural language understanding (NLU) system, in which the system's rules are learnt automatically from training data. The method has been applied to design of a speech understanding (SU) system. Designers of such systems rely increasingly on robust matchers to perform the task of extracting meaning from one or several word sequence hypotheses generated by a speech recognizer; a robust matcher processes semantically important islands of words and constituents rather than attempting to parse the entire word sequence.


Cite as: Kuhn, R., Mori, R.D. (1994) Recent results in automatic learning rules for semantic interpretation. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 75-78

@inproceedings{kuhn94_icslp,
  author={Roland Kuhn and Renato De Mori},
  title={{Recent results in automatic learning rules for semantic interpretation}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={75--78}
}