<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1128">
  <Title>Detection of Question-Answer Pairs in Email Conversations</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 Previous and Related Work
</SectionTitle>
    <Paragraph position="0"> (Muresan et al., 2001) describe work on summarizing individual email messages using machine learning approaches to learn rules for salient noun phrase extraction. In contrast, our work aims at summarizing whole threads and at capturing the interactive nature of email.</Paragraph>
    <Paragraph position="1"> (Nenkova and Bagga, 2003) present work on generating extractive summaries of threads in archived discussions. A sentence from the root message and from each response to the root is extracted using ad-hoc algorithms crafted by hand. This approach works best when the subject of the root email best describes the issue of the thread, and when the root email does not discuss more than one issue. In our work, we do not make any assumptions about the nature of the email, and try to learn strategies to link question and answer segments for summarization. null (Newman and Blitzer, 2003) also address the problem of summarizing archived discussion lists.</Paragraph>
    <Paragraph position="2"> They cluster messages into topic groups, and then extract summaries for each cluster. The summary of a cluster is extracted using a scoring metric based on sentence position, lexical similarity of a sentence to cluster centroid, and a feature based on quotation, among others. Because the summaries are extractive in nature, this approach still suffers from the possibility of incomplete summaries.</Paragraph>
    <Paragraph position="3"> (Lam et al., 2002) present work on email summarization by exploiting the thread structure of email conversation and common features such as named entities and dates. They summarize the message only, though the content of the message to be summarized is expanded using the content from its ancestor messages. The expanded message is passed to a document summarizer which is used as a black box to generate summaries. Our work, in contrast, aims at summarizing the whole thread, and we are precisely interested in changing the summarization algorithm itself, not in using a black box summarizer. null In addition, there has been some work on summarizing meetings. As discussed in Section 1, email is different in important respects from multi-party dialog. However, some important aspects are related.</Paragraph>
    <Paragraph position="4"> (Zechner and Lavie, 2001), for example, presents a spoken dialogue summarization system that takes into consideration local cross-speaker coherence by linking question answer pairs, and uses this information to generate extract based summaries with complete question-answer regions. While we have used a similar question detection approach, our approach to answer detection is different. We get back to this in Section 4.</Paragraph>
    <Paragraph position="5"> (Rambow et al., 2004) show that sentence extraction techniques can work for summarizing email threads, but pro t from email-speci c features. In addition, they show that the presentation of the summary should take into account the dialogic structure of email communication. However, since their approach does not try to detect question and answer pairs, the extractive summaries suffer from the possibility of incomplete summaries.</Paragraph>
  </Section>
class="xml-element"></Paper>