<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-1712">
  <Title>A New E-learning Paradigm through Annotating Operations Hiroaki Saito, Kyoko Ohara, Kengo Sato, Kazunari Ito, Shinsuke Hizuka</Title>
  <Section position="3" start_page="0" end_page="0" type="metho">
    <SectionTitle>
2 System Overview
</SectionTitle>
    <Paragraph position="0"> Here we consider the debate discussion for a foreign language class as an example. This course was originally taught in a regular classroom and through an electronic chatting board supervised by a human instructor. One student posts his/her thought in English and others express positive or negative responses to it. Since this is a foreign language apprehension class, the instructor corrects the students' English if necessary. Since students express various opinions, we cannot prepare for them in advance.</Paragraph>
    <Paragraph position="1"> The instructor was occupied with correcting syntactic errors, therefore, the instructor could not thoroughly pay attention to the ow of the debate or to whether students had appropriately expressed their opinions.</Paragraph>
    <Paragraph position="2"> In Figure 1 example debate submissions are shown on the topic \English should be taught at an elementary school.&amp;quot; #n indicates the submitted order and P1, P2, ... stand for the identi er of the debaters.</Paragraph>
    <Paragraph position="3"> (We will further explain Figure 1 later.) Our system is designed for multi-user discussion, not for self-learning. Thus, we divide the system into the server and the client machines as shown in Figure 2 (only one client machine is drawn in the gure). The server machine manages the contents and handles computationally heavy NLP, while each client machine is responsible for user interface.</Paragraph>
    <Paragraph position="4"> We have developed an e-learning system which offers the process above. Here we describe ve important modules: Sentence analysis module: In this module the input sentences are parsed and tagged syntactically and semantically in the GDA (Global Document Annotation) [4] format. We have adopted the Charniak parser [5], which is customized so that the head word is identi ed because the GDA tagging requires the attachment direction between phrases. The GDA tagger consults the WordNet [6] to nd the root form of a word. GDA tags can be utilized for such further NLP as high quality summarization or information retrieval [7].</Paragraph>
    <Paragraph position="5"> KWIC module: Novice English learners often make such mistakes in collocations and in phrasal verbs. These word-usage mistakes can be e ectively resolved by looking at example sentences rather than by consulting a regular dictionary. This module presents the corpus sentences in the KWIC (KeyWord in Context) format in which the speci ed words are included. Although any corpus will do for KWIC, we have chosen the EDR English corpus [8] which consists of 125,820 tagged sentences. Because the root form of each word is described as a tag, conjugated forms are also searched.</Paragraph>
    <Paragraph position="6"> Annotation module: The instructor corrects the wrong usages of the students' English. This op- null might lower their total achievement.</Paragraph>
    <Paragraph position="7"> I disagree with teaching English at an elementary school. more effectively tought in a junior high school also. Current curriculum of teaching English is not effective enough. I agree that the method of teaching English should be improved. However, if the similar improvement is performed against other subjects, early  ing the originals. Preserving the originals is effective for education; it can prevent other students from making the similar mistakes. When the debater expresses his opinion against/for someone else's, that operation is also observed and attached to the contents, which will be exploited by NLP.</Paragraph>
    <Paragraph position="8"> Interface module: This module enables the user to type in sentences, specify what part he is arguing about, express his/her attitude, etc, efciently. This module displays the contents effectively according to the needs of the user with the help of annotations. Our current interface snapshot is shown in Figure 3.</Paragraph>
    <Paragraph position="9"> Debate Flow module It is important to know the debate ow when one expresses his/her opinion. Since the relations among statements are annotated, precise analysis of the debate ow is possible.</Paragraph>
    <Paragraph position="10"> In the following sections, the annotation module is explained deeply.</Paragraph>
    <Paragraph position="11"> 3 Annotation by the Instructor and Students When a student expresses his/her opinion in response to someone else's, he can specify and denote what part he is arguing about. This linkage is annotated by the user and recorded in the contents. The corrections/comments by the instructor are also stored in the learning contents as annotations. Arrows in Figure 1 show the relation of statements, where a dotted line expresses the linkage denoted by the instructor, and solid lines mean that the debater speci ed those relations.</Paragraph>
  </Section>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
4 The Tag Set for Debate
</SectionTitle>
    <Paragraph position="0"> We have de ned a tag set for annotating debates in an XML format called KeML (Keio e-learning Markup Language). Here we describe our tag set along with how each tag is attached through operations by the instructor or students.</Paragraph>
    <Paragraph position="1"> &lt;debate&gt; encloses the whole debate and is attached when a new debate starts. No attribute is allowed. Possible child-nodes are one &lt;proposition&gt;and zero or more&lt;statement&gt;s.</Paragraph>
    <Paragraph position="2"> &lt;proposition&gt; is attached when a new proposition is submitted. Its mandatory attribute is 'id' and whose value is always '0'. Its child-node is &lt;su&gt; of GDA. The instructor or students should remark the proposition as pros or cons.</Paragraph>
    <Paragraph position="3"> &lt;statement&gt; This tag is attached when a statement to a proposition or other statements is submitted by the instructor or students. Its mandatory attributes are 'attitude' whose value would be pro or con, 'person' whose value indicates who submitted that statement, 'time' which indicates when that statement was given, and 'id' number (an integer). The values of the rst two attributes are given by the user explicitly, while those of the last two are lled by the system. Its optional attributes are 'approval', 'refutation', 'supplement', 'summary', 'question', and 'answer' (some of those attributes appear in Figure 1). They are expressed as \approval=target id&amp;quot; for example. Its child-node is &lt;su&gt; of GDA.</Paragraph>
    <Paragraph position="4"> Such tags below the &lt;su&gt; level as &lt;np&gt; or &lt;v&gt; are attached by the parser according to the GDA speci cations. Every tag must have 'id' attribute and its value is lled automatically by the server.</Paragraph>
    <Paragraph position="5"> Appendix shows the annotated contents of the debate example in Figure 1.</Paragraph>
  </Section>
  <Section position="5" start_page="0" end_page="0" type="metho">
    <SectionTitle>
5 Preserving Corrected Contents
</SectionTitle>
    <Paragraph position="0"> In order that a novice student could observe mistakes by other students, our system preserves the original contents and shows them e ectively when needed. While some mistakes are obvious, others are not. Only the instructor can correct or comment those errors and KeML o ers two levels of correction preservation. Obvious mistakes are stored as the value of 'original' attribute; '&lt;np original=&amp;quot;tought&amp;quot; ..&gt;taught&lt;/np&gt;' for instance. Unobvious mistakes are commented in the value of 'comment' attribute; '&lt;su comment=&amp;quot;This is a comment for this sentence.&amp;quot; ....&lt;/su&gt;' for example. When further correction is made against already corrected contents, only the very rst version is preserved. Our current implementation allows the correction/comments under &lt;su&gt; nodes.</Paragraph>
  </Section>
class="xml-element"></Paper>