EM Works for Pronoun Anaphora Resolution

Eugene Charniak (Brown University) EM (the Expectation Maximization Algorithm) is a well known technique for unsupervised learning (where one does not have any hand labeled solutions available, but instead one must learn from the raw text). Unfortunately EM is known to fail to find good solutions in many (most?) applications on which it is tried. In this talk I present work on using EM to learn how to resolve pronoun-anaphora, for example, determining that “the dog” is the antecedent of “he” and “his” in “When Sally fed the dog he wagged his tail.” For this application EM works strikingly well, determining tens of thousands of parameters and resulting in a program that produces state of the art performance.