... in combination with
50
Proceedings of EACL '99
Automatic Verb Classification Using
Distributions ofGrammaticalFeatures
Suzanne Stevenson
Dept of Computer Science
and Center for Cognitive ... counterpart of the
46
Proceedings of EACL '99
tion of overlap between the two multisets of nouns
was calculated, meant to capture the property of
the causative construction that the subject of ...
excess of 65 million words, with the exception of
causativity which was counted only for the 1988
year of the WSJ, a corpus of 29 million words.
3.2 Method
We counted the occurrences of each...
... Comparison of the perplexity between
models with grammaticalfeatures and models
without grammaticalfeatures for WSME mod-
els over part of the WSJ corpus. N means fea-
tures of n-grams, T means features ... represents the set offeatures used. The
second row shows the perplexity of the models
without using grammatical features. The third
row shows the perplexity of the models using
grammatical features and ... two
kinds of models compared were the grammatical
features, then we conclude that the improvement
must be due to the inclusion of such features into
the set of features. The average percentage of im-
provement...