<?xml version="1.0" standalone="yes"?>
<Paper uid="N03-1022">
  <Title>COGEX: A Logic Prover for Question Answering</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
Motivation
</SectionTitle>
    <Paragraph position="0"> In spite of significant advances made recently in the Question Answering technology, there still remain many problems to be solved. Some of these are: bridging the gap between question and answer words, pinpointing exact answers, taking into consideration syntactic and semantic roles of words, better answer ranking, answer justification, and others. The recent TREC results (Voorhees 2002) have demonstrated that many performing systems reached a plateau; the systems ranked from 4th to 14th answered correctly between 38.4% to 24.8% of the total number of questions. It is clear that new ideas based on a deeper language understanding are necessary to push further the QA technology.</Paragraph>
    <Paragraph position="1"> In this paper we introduce one such novel idea, the use of automated reasoning in QA, and show that it is feasible, effective, and scalable. We have implemented a Logic Prover, called COGEX (from the permutation of the first two syllables of the verb excogitate) which uniformly codifies the question and answer text, as well as world knowledge resources, in order to use its inference engine to verify and extract any lexical relationships between the question and its candidate answers.</Paragraph>
    <Paragraph position="2"> Usefulness of a Logic Prover in QA COGEX captures the syntax-based relationships such as the syntactic objects, syntactic subjects, prepositional attachments, complex nominals, and adverbial/adjectival adjuncts provided by the logic representation of text. In addition to the logic representations of questions and candidate answers, the QA Logic Prover needs world knowledge axioms to link question concepts to answer concepts. These axioms are provided by the WordNet glosses represented in logic forms. Additionally, the prover needs rewriting procedures for semantically equivalent lexical patterns. With this deep and intelligent representation, COGEX effectively and efficiently re-ranks candidate answers by their correctness, extracts the exact answer, and ultimately eliminates incorrect answers. In this way, the Logic Prover is a powerful tool in boosting the accuracy of the QA system. Moreover, the trace of a proof constitutes a justification for that answer.</Paragraph>
    <Paragraph position="3"> Technical challenges The challenges one faces when using automated reasoning in the context of NLP include: logic representation of open text, need of world knowledge axioms, logic representation of semantically equivalent linguistic patterns, and others. Logic proofs are accurate but costly, both in terms of high failure rate due to insufficient input axioms, as well as long processing time. Our solution is to integrate the prover into the QA system and rely on reasoning methods only to augment other previously implemented answer extraction techniques.</Paragraph>
  </Section>
class="xml-element"></Paper>