File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/intro/04/w04-2504_intro.xml
Size: 3,567 bytes
Last Modified: 2025-10-06 14:02:45
<?xml version="1.0" standalone="yes"?> <Paper uid="W04-2504"> <Title>Discourse Structure for Context Question Answering</Title> <Section position="2" start_page="0" end_page="0" type="intro"> <SectionTitle> 1 Introduction </SectionTitle> <Paragraph position="0"> In a real-world setting, questions are not asked in isolation, but rather in a cohesive manner that involves a sequence of related questions to meet user's information needs. The capability to interpret and answer questions based on context is important.</Paragraph> <Paragraph position="1"> For example, Figure 1 shows an example of a series of context questions. In this example, the interpretation of Q2 and Q4 depends on the resolution of &quot;it&quot; and &quot;this&quot; from the context respectively. Although neither Q3 nor Q6 requires any anaphora resolution, the interpretation of Q3 depends on Q2 while the interpretation of Q6 depends solely on itself. Furthermore, in Q5, there are no explicit references. Its interpretation depends on a preceding question (e.g.,Q4), however, in a different manner.</Paragraph> <Paragraph position="2"> This example indicates that interpreting each of these questions and extracting answers needs to be situated in a particular context as the QA session proceeds. There are situations where a question is &quot;complete&quot; enough and its interpretation does not depend on the previous questions (Q6). There are also situations where the interpretation of a question depends on preceding questions no matter whether it requires anaphora or ellipsis resolution. Based on these observations, a natural question to ask is what makes the use of discourse differently in different situations? What is the role of discourse in context question answering? To address these questions, a key issue, in our mind, is that every question and its answer have a discourse status with respect to an entire QA session. This discourse status includes two aspects. The first aspect relates to discourse roles of entities in a question and the corresponding answer. Entities (such as noun phrase, verb phrase, preposition phrase, etc) in a question carry distinctive roles that indicate what is the topic or focus of a question in terms of the overall information seeking discourse. Topic relates to the &quot;aboutness&quot; of a question and focus relates to a specific perspective of the topic. The second aspect of discourse status relates to discourse transitions that indicate how discourse roles are changed from one question to another as the interaction proceeds and how such changes reflect the progress of user information needs. Both discourse roles and discourse transitions determine whether the context is useful, and if so, how to use the context to interpret a question.</Paragraph> <Paragraph position="3"> This paper takes an initial attempt to investigate the discourse status for context question answering.</Paragraph> <Paragraph position="4"> In particular, it motivates a semantic-rich discourse representation that captures both discourse roles of a question and discourse transitions between questions.</Paragraph> <Paragraph position="5"> Through examples, this paper further discusses the potential impact of this refined discourse structure on context question answering.</Paragraph> <Paragraph position="6"> Q1: What is the name of the volcano that destroyed the ancient city of Pompeii? Q2: When did it happen? Q3: how many people were killed? Q4: how tall was this volcano?</Paragraph> </Section> class="xml-element"></Paper>