<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-1072">
  <Title>Splitting Complex Temporal Questions for Question Answering systemsa0</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Question Answering could be defined as the process of computer-answering to precise or arbitrary questions formulated by users. Q.A. systems are especially useful to obtain a specific piece of information without the need of manually going through all the available documentation related to the topic.</Paragraph>
    <Paragraph position="1"> Research in Question Answering mainly focuses on the treatment of factual questions. These require as an answer very specific items of data, such as dates, names of entities or quantities, e.g., &amp;quot;What is the capital of Brazil?&amp;quot;.</Paragraph>
    <Paragraph position="2"> a3 This paper has been supported by the Spanish government, projects FIT-150500-2002-244, FIT-150500-2002-416, TIC2003-07158-C04-01 and TIC2000-0664-C02-02.</Paragraph>
    <Paragraph position="3"> Temporal Q.A. is not a trivial task due to the complexity temporal questions may reach. Current operational Q.A. systems can deal with simple factual temporal questions. That is, questions requiring to be answered with a date, e.g. &amp;quot;When did Bob Marley die?&amp;quot;. or questions that include simple temporal expressions in their formulation, e.g., &amp;quot;Who won the U.S. Open in 1999?&amp;quot;. Processing this sort of questions is usually performed by identifying explicit temporal expressions in questions and relevant documents, in order to gather the necessary information to answer the queries.</Paragraph>
    <Paragraph position="4"> Even though, it seems necessary to emphasize that the system described in (Breck et al., 2000) is the only one also using implicit temporal expression recognition for Q.A. purposes. It does so by applying the temporal tagger developed by Mani and Wilson (2000).</Paragraph>
    <Paragraph position="5"> However, issues like addressing the temporal properties or the ordering of events in questions, remain beyond the scope of current Q.A. systems:  This work presents a Question Answering system capable of answering complex temporal questions.</Paragraph>
    <Paragraph position="6"> This approach tries to imitate human behavior when responding this type of questions. For example, a human that wants to answer the question: &amp;quot;Who was spokesman of the Soviet Embassy in Baghdad during the invasion of Kuwait?&amp;quot; would follow this process:  1. First, he would decompose this question into two simpler ones: &amp;quot;Who was spokesman of the Soviet Embassy in Baghdad?&amp;quot; and &amp;quot;When did the invasion of Kuwait occur?&amp;quot;.</Paragraph>
    <Paragraph position="7"> 2. He would look for all the possible answers to the first simple question: &amp;quot;Who was spokesman of the Soviet Embassy in Baghdad?&amp;quot;. null 3. After that, he would look for the answer to the second simple question: &amp;quot;When did the invasion of Kuwait occur?&amp;quot; 4. Finally, he would give as a final answer one  of the answers to the first question (if there is any), whose associated date stays within the period of dates implied by the answer to the second question. That is, he would obtain the final answer by discarding all answers to the simple questions which do not accomplish the restrictions imposed by the temporal signal provided by the original question (during).</Paragraph>
    <Paragraph position="8"> Therefore, the treatment of complex question is based on the decomposition of these questions into simpler ones, to be resolved using conventional Question Answering systems. Answers to simple questions are used to build the answer to the original question.</Paragraph>
    <Paragraph position="9"> This paper has been structured in the following fashion: first of all, section 2 presents our proposal of a taxonomy for temporal questions. Section 3 describes the general architecture of our temporal Q.A. system. Section 4 deepens into the first part of the system: the decomposition unit. Finally, the evaluation of the decomposition unit and some conclusions are shown.</Paragraph>
    <Paragraph position="10"> 2 Proposal of a Temporal Questions Taxonomy Before explaining how to answer temporal questions, it is necessary to classify them, since the way to solve them will be different in each case. Our classification distinguishes first between simple questions and complex questions. We will consider as simple those questions that can be solved directly by a current General Purpose Question Answering system, since they are formed by a single event. On the other hand, we will consider as complex those questions that are formed by more than one event related by a temporal signal which establishes an order relation between these events.</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
Simple Temporal Questions:
</SectionTitle>
      <Paragraph position="0"> temporal expression (TE). This kind of questions are formed by a single event and can be directly resolved by a Q.A. System, without pre- or post-processing them. There are not temporal expressions in the question. Example: &amp;quot;When did Jordan close the port of Aqaba to Kuwait?&amp;quot; Type 2: Single event temporal questions with temporal expression. There is a single event in the question, but there are one or more temporal expressions that need to be recognized, resolved and annotated.</Paragraph>
      <Paragraph position="1"> Each piece of temporal information could help to search for an answer. Example: &amp;quot;Who won the 1988 New Hampshire republican primary?&amp;quot;. TE: 1988 Complex Temporal Questions: Type 3: Multiple events temporal questions with temporal expression. Questions that contain two or more events, related by a temporal signal. This signal establishes the order between the events in the question. Moreover, there are one or more temporal expressions in the question. These temporal expressions need to be recognized, resolved and annotated, and they introduce temporal constraints to the answers of the question. Example: &amp;quot;What did George Bush do after the U.N. Security Council ordered a global embargo on trade with Iraq in August 90?&amp;quot; In this example, the temporal signal is after and the temporal constraint is &amp;quot;between 8/1/1990 and 8/31/1990&amp;quot;. This question can be divided into the following ones: a4 Q1: What did George Bush do? a4 Q2: When the U.N. Security Council ordered a global embargo on trade with Iraq? Type 4: Multiple events temporal questions without temporal expression. Questions that consist of two or more events, related by a temporal signal. This signal establishes the order between the events in the question. Example: &amp;quot;What happened to world oil prices after the Iraqi annexation of Kuwait?&amp;quot;. In this example, the temporal signal is after and the question would be decomposed into: a4 Q1: What happened to world oil prices? a4 Q2: When did the Iraqi &amp;quot;annexation&amp;quot; of Kuwait occur? How to process each type will be explained in detail in the following sections.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>