<?xml version="1.0" standalone="yes"?>
<Paper uid="H05-2003">
  <Title>Introducing Discussion Summarization to Online Classrooms</Title>
  <Section position="3" start_page="4" end_page="4" type="metho">
    <SectionTitle>
2 Summarization Framework
</SectionTitle>
    <Paragraph position="0"> In this section, we will give a brief description of the discussion summarization framework that is applied to online classroom discussions.</Paragraph>
    <Paragraph position="1"> One important component in the original system (Zhou and Hovy, 2005) is the sub-message clustering. The original chat logs are in-depth technical discussions that often involve multiple sub-topics, clustering is used to model this behavior. In Classummary, the discussions are presented in an organized fashion where users only respond to and comment on specific topics. Thus, it eliminates the need for clustering.</Paragraph>
    <Paragraph position="2"> All messages in a discussion are related to the central topic, but to varying degrees. Some are answers to previously asked questions, some make suggestions and give advice where they are requested, etc. We can safely assume that for this type of conversational interactions, the goal of the participants is to seek help or advice and advance their current knowledge on various course-related subjects. This kind of interaction can be modeled as one problem-initiating message and one or more corresponding problem-solving messages, formally defined as Adjacent Pairs (AP). A support vector machine, pre-trained on lexical and structural features for OSS discussions, is used to identify the most relevant responding messages to the initial post within a topic.</Paragraph>
    <Paragraph position="3"> Having obtained all relevant responses, we adopt the typical summarization paradigm to extract informative sentences to produce concise summaries. This component is modeled after the BE-based multi-document summarizer (Hovy et al., 2005). It consists of three steps. First, important basic elements (BEs) are identified according to their likelihood ratio (LR). BEs are automatically created minimal semantic units of the form head-modifier-relation (for example, &amp;quot;Libyans | two  |nn&amp;quot;, &amp;quot;indicted  |Libyans  |obj&amp;quot;, and &amp;quot;indicted  |bombing  |for&amp;quot;). Next, each sentence is given a score which is the sum of its BE scores, computed in the first step, normalized by its length. Lastly, taking into consideration the interactions among summary sentences, a MMR (Maximum Marginal Relevancy) model (Goldstein et al., 1999) is used to extract sentences from the list of top-ranked sentences computed from the second step.</Paragraph>
  </Section>
  <Section position="4" start_page="4" end_page="4" type="metho">
    <SectionTitle>
3 Accessibility
</SectionTitle>
    <Paragraph position="0"> Classummary is accessible to students and teachers while classes are in session. At HLT, we will demonstrate an equivalent web-based version. Discussions are displayed on a per-topic basis; and messages belonging to a specific discussion are arranged in ascending order according to their timestamps. While viewing a new message on a topic, the user can choose to receive a summary of the discussion so far or an overall summary on the topic. Upon receiving the summary (for students, at the end of an academic term), a list of questions is presented to the user to gather comments on whether Classummary is useful. We will show the survey results from the classes (which will have concluded by then) at the conference.</Paragraph>
  </Section>
class="xml-element"></Paper>