Paper: Smoothing Of Automatically Generated Selectional Constraints

ACL ID H93-1050
Title Smoothing Of Automatically Generated Selectional Constraints
Venue Human Language Technologies
Session Main Conference
Year 1993
Authors

Frequency information on co-occurrence patterns can be automati- cally collected from a syntactically analyzed corpus; this information can then serve as the basis for selectional constraints when analyz- ing 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 au- tomatically make suitable generalizations: using the co-occurrence data to compute a confusion matrix relating individual words, and then using the confusion matrix to smooth the original frequency data.