We first describe paraphrase acquisition, we then summarize our method for learning surface patterns, and finally describe the use of patterns for extracting relation instances .

To compare the quality of the extraction patterns, and relation instances , we use the method presented by Ravichandran and Hovy (2002) as the baseline.

The intuition is that applying the vague patterns for extracting target relation instances might find some good instances, but will also find many bad ones.

Using distributional similarity avoids the problem of obtaining overly general patterns and the pre-computation of paraphrases means that we can obtain the set of patterns for any relation instantaneously .

While procedurally different, both methods depend heavily on the performance of the syntax parser and require complex syntax tree matching to extract the relation instances .