<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-2017">
  <Title>Towards Interactive Text Understanding</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Answering emails sent to a company by its customers -- to take just one example among many similar text-processing tasks -- requires a reliable understanding of the content of incoming messages. This understanding can currently only be done by humans, and represents the main bottleneck to a complete automation of the processing chain: other aspects could be delegated to such procedures as database requests and text generation. Current technology in natural language understanding or in information extraction is not at a stage where the understanding task can be accomplished reliably without human intervention. null In this paper, which aims at proposing a fresh outlook on the problem of text understanding rather than at describing a completed implementation, we advocate an interactive approach where:  1. The building of the semantic representation is under the control of a human author; 2. In order to build the semantic representa- null tion, the author interacts with an intuitive textual interface to that representation (obtained from it through an NLG process), where some &amp;quot;active&amp;quot; regions of the text are associated with menus that display a number of semantic choices for incrementing the representation; 3. The raw input text to be analyzed serves as a source of information to the authoring system and permits to associate likelihood levels with the various authoring choices; in each menu the choices are then ranked according to their likelihood, allowing a speedier selection by the author; when the likelihood of a choice exceeds a certain threshold, this choice is performed automatically by the system (but in a way that remains revisable by the author).</Paragraph>
    <Paragraph position="1"> 4. The system acts as a flexible understanding aid to the human operator: by tuning the threshold at a low level, it can be used as a purely automatic, but somewhat unreliable, information extraction or understanding system; by tuning the threshold higher, it can be used as a powerful interactive guide to building a semantic interpretation, with the advantage of a plain textual interface to that representation that is easily accessible to general users.</Paragraph>
    <Paragraph position="2"> The paper is organized as follows. In section 2, we present a document authoring system, MDA, where the author constructs an internal semantic representation, but interacts with a textual realization of that representation. In section 3, we explain how such a system may be extended into an Interactive Text Understanding (ITU) aid. A raw input document acts as an information source that serves to rank the choices proposed to the author according to their likelihood of &amp;quot;accounting&amp;quot; for information present in the input document. In section 4, we present current work on using MDA for legacy-document normalization and show that this work can provide a first approach to an ITU implementation. In section 5, we indicate some links between these ideas and current work on interactive statistical MT (TransType), showing directions towards more efficient implementations of ITU.</Paragraph>
  </Section>
class="xml-element"></Paper>