Smoothing of Automatically Generated Selectional Constraints

  title={Smoothing of Automatically Generated Selectional Constraints},
  author={Ralph Grishman and John Sterling},
Frequency information on co-occurrence patterns can be automatically collected from a syntactically analyzed corpus; this information can then serve as the basis for selectional constraints when analyzing new text from the same domain. Better coverage of the domain can be obtained by appropriate generalization of the specific word patterns which are collected. We report here on an approach to automatically make suitable generalizations: using the co-occurrence data to compute a confusion matrix… CONTINUE READING

Figures, Tables, and Topics from this paper.

Explore Further: Topics Discussed in This Paper


Publications citing this paper.


Publications referenced by this paper.