NLP systems for tasks such as question answering and information extraction typ- ically rely on statistical parsers. But the ef- ficacy of such parsers can be surprisingly low, particularly for sentences drawn from heterogeneous corpora such as the Web. We have observed that incorrect parses of- ten result in wildly implausible semantic interpretations of sentences, which can be detected automatically using semantic in- formation obtained from the Web. Based on this observation, we introduce Web-based semantic filtering—a novel, domain-independent method for automat- ically detecting and discarding incorrect parses. We measure the effectiveness of our filtering system, called WOODWARD, on two test collections. On a set of TREC questions, it reduces error by 67%. On a set of more complex ...

Click Here to View the Paper In XML Format