Multistrategy Learning for Information Extraction

Information extraction IE is the problem of lling out pre de ned structured sum maries from text documents We are in terested in performing IE in non traditional domains where much of the text is often ungrammatical such as electronic bulletin board posts and Web pages We suggest that the best approach is one that takes into ac count many di erent kinds of information and argue for the suitability of a multistrat egy approach We describe learners for IE drawn from three separate machine learning paradigms rote memorization term space text classi cation and relational rule induc tion By building regression models mapping from learner con dence to probability of cor rectness and combining probabilities appro priately it is possible to improve extraction accuracy over that achieved by any individ ual learner We describe three di erent mul tistrategy approaches Experiments on two IE domains a collection of electronic seminar announcements from a university computer science department and a set of newswire ar ticles describing corporate acquisitions from the Reuters collection demonstrate the e ec tiveness of all three approaches