<?xml version="1.0" standalone="yes"?>
<Paper uid="P00-1070">
  <Title>Importance of Pronominal Anaphora resolution in Question Answering systems</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 Background
</SectionTitle>
    <Paragraph position="0"> Interest in open domain QA systems is quite recent. We had little information about this kind of systems until the First Question Answering Trackwas held in last TREC conference #28TRE, 1999#29. In this conference, nearly twenty di#0Berent systems were evaluated with very di#0Berent success rates. We can classify current approaches into two groups: text-snippet extraction systems and noun-phrase extraction systems.</Paragraph>
    <Paragraph position="1"> Text-snippet extraction approaches are based on locating and extracting the most relevant sentences or paragraphs to the query by supposing that this text will contain the correct answer to the query. This approach has been the most commonly used by participants in last TREC QA Track. Examples of these systems are #28Moldovan et al., 1999#29 #28Singhal et al., 1999#29 #28Prager et al., 1999#29 #28Takaki, 1999#29 #28Hull, 1999#29 #28Cormack et al., 1999#29. After reviewing these approaches, we can notice that there is a general agreement about the importance of several Natural Language Processing #28NLP#29 techniques for QA task. Pos-tagging, parsing and Name Entity recognition are used by most of the systems. However, few systems apply other NLP techniques. Particularly, only four systems model some coreference relations between entities in the query and documents #28Morton, 1999#29#28Breck et al., 1999#29 #28Oard et al., 1999#29 #28Humphreys et al., 1999#29. As example, Morton approach models identity, de#0Cnite noun-phrases and non-possessive third person pronouns. Nevertheless, bene#0Cts of applying these coreference techniques have not been analysed and measured separately.</Paragraph>
    <Paragraph position="2"> The second group includes noun-phrase extraction systems. These approaches try to #0Cnd the precise information requested by questions whose answer is de#0Cned typically by a noun phrase.</Paragraph>
    <Paragraph position="3"> MURAX is one of these systems #28Kupiec, 1999#29. It can use information from di#0Berent sentences, paragraphs and even di#0Berentdocuments to determine the answer #28the most relevant noun-phrase#29 to the question. However, this system does not take into account the information referenced pronominally in documents. Simply, it is ignored.</Paragraph>
    <Paragraph position="4"> With our system, wewant to determine the bene#0Cts of applying pronominal anaphora resolution techniques to QA systems. Therefore, we apply the developed computational system, Slot Uni#0CcationParser for Anaphora resolution #28SUPAR#29 over documents and queries #28Ferr#13andez et al., 1999#29. SUPAR's architecture consists of three independent modules: lexical analysis, syntactic analysis, and a resolution module for natural language processing problems, such as pronominal anaphora.</Paragraph>
    <Paragraph position="5"> For evaluation, a standard based IR system and a sentence-extraction QA system have been implemented. Both are based on Salton approach #281989#29. After IR system retrieves relevant documents, our QA system processes these documents with and without solving pronominal references in order to compare #0Cnal performance.</Paragraph>
    <Paragraph position="6"> As results will show, pronominal anaphora resolution improves greatly QA systems performance. So, we think that this NLP technique should be considered as part of any open domain QA system.</Paragraph>
  </Section>
class="xml-element"></Paper>