<?xml version="1.0" standalone="yes"?>
<Paper uid="W01-1012">
  <Title>What are the points? What are the stances? Decanting for question-driven retrieval and executive summarization</Title>
  <Section position="3" start_page="0" end_page="0" type="metho">
    <SectionTitle>
ACTORS AND QUOTES
</SectionTitle>
    <Paragraph position="0"> The peace process will take time [cause_from] Barak and Arafat have different standpoints.</Paragraph>
    <Paragraph position="1"> The peace process will take time[detract] Barak and Arafat want a peaceful resolution.</Paragraph>
    <Paragraph position="2"> } NB The utterer of the last assertions is the author of the input text. If we process multiple texts, we have to indicate it explicitly (author  As of the submission of this article, the prototype detects the quotes but not the stances and contexts (which functionalities are under development).</Paragraph>
  </Section>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
6 Example 2: &amp;quot;What Are the
</SectionTitle>
    <Paragraph position="0"> Comments?&amp;quot; (manual study) This example is to indicate the kind of comparative output targeted (but not implemented as yet), and the series of linguistic and modeling difficulties involved in producing it. It is based on an excerpt from a BBC bulletin board linked, at the time, from news.bbc.co.uk, called &amp;quot;BBC Talking point&amp;quot;, at http://newsvote.bbc.co.uk/hi/english/talking_poi nt.</Paragraph>
    <Paragraph position="1"> The case in point was the desirable attitude towards the participation of Jorg Haider's  - No d-author (author of the page or article) is mentioned, as all the texts in this example are from the same page.</Paragraph>
    <Paragraph position="2"> - Author: author of the comment; identification if free (may be a pseudonym) - Statement: original statement - Marked up statement: statement after insertion of argumentation tags - Summary, manual: freely rephrased (there is also a summary from the BBC editor, which we do not mention here) - Arguments: main justifications, rephrased - Orientation:: here, by convention, pro means  &amp;quot;for&amp;quot; Haider's mandate and against sanctions; NOT necessarily in favour of Haider and his party.</Paragraph>
    <Paragraph position="3">  to isolate Austria.</Paragraph>
    <Paragraph position="4"> Austria is, after all, a full member in good standing of the EU and its new government has not actually committed any acts contrary to EU principles. If the EU starts policing its members over the outcome of due democratic process, who will police the EU when it gets out of  - sanctions are not justified nor legal - Austria is a member of the EU in good standing - no devious acts - Austria is master at home - counterfactual: if EU at large becomes  devious, who will control it? p Pb: the core point maybe less noteworthy or quoteworthy than a justification of it.</Paragraph>
    <Paragraph position="5">  curiously, appears quoted.</Paragraph>
    <Paragraph position="6"> Paradox, from implicit knowledge that the left is normally more principled about liberty than the right.</Paragraph>
    <Paragraph position="7"> Implicit: The EU administration is often not heeding much other levels of decision.</Paragraph>
  </Section>
  <Section position="5" start_page="0" end_page="11" type="metho">
    <SectionTitle>
7 Jaya N.,
</SectionTitle>
    <Paragraph position="0"> India I think the EU has reacted responsibly and followed through on its earlier statements. When one country acts in such a way as to promote leaders with outright prejudice, the rest of the Nations must do all in their power to subdue further action. The EU is right, and has been acting consistently, because this is a clear case of prejudice.</Paragraph>
    <Paragraph position="1"> Austria (or the FPO) is prejudiced c Loaded: &amp;quot;outright prejudice.&amp;quot; Reasoning from general (&amp;quot;when one country&amp;quot;) to particular.</Paragraph>
    <Paragraph position="2"> Rem: fails to distinguish between prejudice in the FPO's policy and supposed prejudice of the country as such or in majority.</Paragraph>
    <Section position="1" start_page="7" end_page="7" type="sub_section">
      <SectionTitle>
Evaluation / Commentary
</SectionTitle>
      <Paragraph position="0"> This is prototype work, but several original functionalities are already giving results: - characterizing the topic, based on discriminating keywords - i.e. the system makes good guesses among a dozen topics including economics/finance, economic policy, conflict, social/labour relations, culture, electoral politics...</Paragraph>
      <Paragraph position="1"> - from the topic, predicting typical issues on which stances articulate: for example for economic policy, one may expect stances about deregulation, globalization, interest rates, etc.</Paragraph>
      <Paragraph position="2"> - extracting quotes in direct speech gives 60% good results; on indirect speech, this goes down to about 40%.</Paragraph>
      <Paragraph position="3"> - stance assignment works at about 50% success (good positives).</Paragraph>
      <Paragraph position="4"> Entity-extraction is not particularly original, like finding entities, classifying them, detecting naming equivalences for the entities.</Paragraph>
    </Section>
    <Section position="2" start_page="7" end_page="11" type="sub_section">
      <SectionTitle>
Related work
Philosophy and Critical Thinking
</SectionTitle>
      <Paragraph position="0"> Books on critical thinking (Little et al. 89, Mendenhall 90) use representations of argument structures (e.g. as diagrams) but give no hint as how to automate it, i.e to go from text to model.</Paragraph>
      <Paragraph position="1"> Linguistics and NLP While research in linguistics has addressed several brands of &amp;quot;discourse analysis&amp;quot; as dialogue pragmatics and the search for underlying &amp;quot;ideology&amp;quot; or values, there is little in general linguistics about the study of argumentation proper.</Paragraph>
      <Paragraph position="2"> Simone Teufel (1999) performs &amp;quot;argumentative zoning&amp;quot; on research papers, finding types of passages like: aim, background, own research, continuation. The result is a colour-coded display of the input, based on an XML markup.</Paragraph>
      <Paragraph position="3"> Bayes and ngrams are used to perform this classication task. (Interestingly, she finds good agreement between manual annotators, vs various research in summarization failing to detect &amp;quot;golden standard&amp;quot; summaries.) This is argumentation in a rather specialized (scientific research in AI, i.e., largely, innovation in problem-solving) and shallow (no collation of the points themselves; one-level) sense. In contrast, Decanter is designed to deliver a representation of conclusions and justifications, from several uttererers in parallel or in a nested fashion if applicable.</Paragraph>
      <Paragraph position="4"> Some work on summarization, in particular by Daniel Marcu (Marcu 97) has looked at the &amp;quot;rhetoric&amp;quot; dimension of text, based on RST (Mann&amp;Thompson 88). It produces a detailed and high-quality tree representing the articulation of the text, but it is qualitatively a hybrid: it does not separate argumentation from mere description or narration. The detailed user study and modeling done in (Endres-Nieggemeyer 97) gives little place to argumentation tracking in the summarization process.</Paragraph>
      <Paragraph position="5"> (Barker et al. 94) process rules and examples legal text to produce a semantic output then fed to a machine learning system doing generalization and abstraction. Yet it does not consider contexts of utterance.</Paragraph>
      <Paragraph position="6"> Information retrieval Information has focused even less on argumentation. As indicated above, answering on-topic is useful, but often the user is in fact looking for information which answers a question, which is situated, and which may involve opinions. We know of no work in argumentation-based IR - all the overhead of high-level filtering of argument being left to the user.</Paragraph>
      <Paragraph position="7"> Knowledge Representation and automated reasoning Some authors in computational linguistics have approached contexts. Ballim &amp; Wilks do knowledge representation with nested contexts with Fauconnier's mental spaces. Moulin uses conceptual graphs to represent spatio-temporal contexts from text. (Recently, a student project in his department has addressed argumentation, it seems, but information is scarce). Recently, a contributor to the CG list, L. Misek-Falkoff, asked for tools to represent nested contexts in tort/defamation; there were some answers pointing to tools, but not to tools capable of doing this.</Paragraph>
      <Paragraph position="8"> Various studies of reasoning, on the legal domain like (Bench-Capon 97) or more general like (Zukerman et al. 99), represent sophisticated reasoning, without performing extraction from text.</Paragraph>
      <Paragraph position="9"> (Delannoy 99) proposed an XML mark-up scheme for argumentation as such, the idea being to flag it inside the text besides producing a separate representation. Decanter is designed to do both.</Paragraph>
      <Paragraph position="10">  Future work Further work is intended to address a variety of robustness and scope issues, including reference resolution (neglected in IR) and the detection of lexicalized irony in the expression of stances.  This is another neglected topic in IR. Even medium-quality reference resolution would enhance performance in IR, including in our approach.</Paragraph>
      <Paragraph position="11"> Indirect argumentation and irony Indirect argumentation, especially irony Irony is an ingredient of rhetoric and can be of use in tracking stance on topics, stances on other actors, and also style of course. In another study (Delannoy 2001b) I observe the alternating use of irony and indignation. Besides the direct interest as a study rhetoric, it shows the variance of one factor of enunciation the sociopsychological attitude, while the doxasticepistemic attitude stays aligned (the stance). From an IR point of view, one could try to differentiate ironic from non-ironic passages; also to normalize them into a &amp;quot;just the stance&amp;quot; form - a desalination device of sorts! Conclusion IR and NLP should pay due attention to question-focused information of course, but to other textual elements participating in the value of the returns, both 1) when it gives a useful characterization of the usability of the answer as plausible, corroborated, demonstrated, novel, etc. 2) to begin to answer questions never addressed in IR and CL but definitely pervasive in user needs, either easily phrasable, in the style: &amp;quot;Is Netscape a good tool?&amp;quot;, &amp;quot;Is it advisable to buy Microsoft stock soon?&amp;quot;, or as a more underlying information goal: &amp;quot;So, what is Le Monde saying about the new developments of Plan Colombia and about the political reactions?&amp;quot;. This second type can be useful both to interested layme and to professionals of information and politics.</Paragraph>
      <Paragraph position="12"> Moreover, a matrix presentation as in example 2 can be quite useful and reusable. That is, to be even more useful, argumentation analysis should integrate information retrieval + analysis + aggregation.</Paragraph>
      <Paragraph position="13"> In a Baconian vein: The information retriever and questioner has to use Invention (IR techniques) and Judgment (critical thinking) to tap into Memory (writing, library science) and Tradition (corpus of knowledge, opinions).</Paragraph>
      <Paragraph position="14"> Decanter opens the way to the necessary contribution of Judgment in Invention.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>