|START Conference Manager|
This paper addresses the importance of resource quality through the lens of a challenging NLP task: detecting selectional preference violations. We present DAVID, a simple, lexical resource-based preference violation detector. With as-is lexical resources, DAVID achieves an F1 -measure of just 28.27%. When the resource entries and parser outputs for to a small sample are corrected, however, the F1-measure on that sample jumps from 40% to 61.54%, and performance on other examples rises, suggesting that the algorithm becomes practical given cleaned-up resources. More broadly, this paper shows that resource quality matters tremendously, sometimes even more than algorithmic improvements.
START Conference Manager (V2.61.0 - Rev. 2792M)