A Corpus � Based Approach to Language Learning Eric Brill

A CORPUS BASED APPROACH TO LANGUAGE LEARNING Eric Brill Supervisor Mitchell Marcus One goal of computational linguistics is to discover a method for assigning a rich struc tural annotation to sentences that are presented as simple linear strings of words meaning can be much more readily extracted from a structurally annotated sentence than from a sentence with no structural information Also structure allows for a more in depth check of the well formedness of a sentence There are two phases to assigning these structural annotations rst a knowledge base is created and second an algorithm is used to generate a structural annotation for a sentence based upon the facts provided in the knowledge base Until recently most knowledge bases were created manually by language experts These knowledge bases are expensive to create and have not been used e ectively in structurally parsing sentences from other than highly restricted domains The goal of this dissertation is to make signi cant progress toward designing automata that are able to learn some struc tural aspects of human language with little human guidance In particular we describe a learning algorithm that takes a small structurally annotated corpus of text and a larger unannotated corpus as input and automatically learns how to assign accurate structural descriptions to sentences not in the training corpus The main tool we use to automati cally discover structural information about language from corpora is transformation based error driven learning The distribution of errors produced by an imperfect annotator is examined to learn an ordered list of transformations that can be applied to provide an accurate structural annotation We demonstrate the application of this learning algorithm