<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-2502">
  <Title>Answering Questions Using Advanced Semantics and Probabilistic Inference</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Current Question Answering systems extract answers from large text collections by (1) classifying questions by the answer type they expect; (2) using question keywords or patterns associated with questions to identify candidate answer passages and (3) ranking the candidate answers to decide which passage contains the exact answer. A few systems also justify the answer, by performing abduction in first-order predicate logic [Moldovan et al., 2003]. This paradigm is limited by the assumption that the answer can be found because it uses the question words. Although this may happen sometimes, this assumption does not cover the many cases where an informative answer is missed because its identification requires more sophisticated semantic processing than named entity recognition and the identification of an answer type. Therefore access to rich semantic structures derived from questions and answers will enable the retrieval of more accurate answers as well as inference processes that explain the validity and contextual coverage of answers.</Paragraph>
    <Paragraph position="1"> Several stages of deeper semantic processing may be considered for processing complex questions. A first step in this direction is the incorporation of &amp;quot;semantic parsers&amp;quot; or identifiers of predicate argument structures in the processing of both questions and documents.</Paragraph>
    <Paragraph position="2"> Processing complex questions consists of: (1) a syntactic parse of the question and of the document collection; (2) Named Entity recognition that along with the syntactic parse enable (3) the identification of predicate-argument structures; and (4) identification of the answer types, which no longer consist of simple concepts, but rather complex conceptual structures, and (5) keywords extraction that allows candidate answers to be identified. Document processing is performed by indexing and retrieval that uses three forms of semantic information: (1) Classes of named entities; (2) Predicate-argument structures and (3) Ontologies of possible answer types. Additionally, as more complex semantic structures are evoked by the question and recognized in documents, indexing and retrieval models are enhanced by taking into account conceptual schemas and topic models. Answer processing is concerned with the recognition of the answer structure, which is a natural extension of recognizing exact answers when they are represented as single concepts. Since many times the answer is merged from several sources, enhanced answer processing also requires a set of special operators for answer fusion.</Paragraph>
    <Paragraph position="3"> The rest of the paper is organized as follows. Section 2 presents question processing that uses deeper semantic resources. Section 3 details the methods for answer extraction whereas Section 4 describes methods for representing and reasoning with rich semantic structures.</Paragraph>
    <Paragraph position="4"> Section 5 summarizes the conclusions.</Paragraph>
  </Section>
class="xml-element"></Paper>