Can Selectional Preferences Help Automatic Semantic Role Labeling?
Shumin Wu, Martha Stone Palmer · 2015
We describe a topic model based approach for selectional preference. Using the topic features generated by an LDA model on the extracted predicate-arguments over the Chinese Gigaword corpus, we show improvement to our state-of-the-art Chinese SRL system by 2.34 F1 points on arguments of nominal predicates, 0.40 F1 point on arguments of verb predicates, and 0.66 F1 point overall. More over, similar gains were achieved on out-ofgenre test data, as well as on English SRL using the same technique.