<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0618">
  <Title>Beyond the Pipeline: Discrete Optimization in NLP</Title>
  <Section position="4" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> NLP applications involve mappings between complex representations. In generation a representation of the semantic content is mapped onto the grammatical form of an expression, and in analysis the semantic representation is derived from the linear structure of a text or utterance. Each such mapping is typically split into a number of different tasks handled by separate modules. As noted by Daelemans &amp; van den Bosch (1998), individual decisions that these tasks involve can be formulated as classi cation problems falling in either of two groups: disambiguation or segmentation. The use of machine-learning to solve such tasks facilitates building complex applications out of many light components. The architecture of choice for such systems has become a pipeline, with strict ordering of the processing stages. An example of a generic pipeline architecture is GATE (Cunningham et al., 1997) which provides an infrastructure for building NLP applications. Sequential processing has also been used in several NLG systems (e.g. Reiter (1994), Reiter &amp; Dale (2000)), and has been successfully used to combine standard preprocessing tasks such as part-of-speech tagging, chunking and named entity recognition (e.g. Buchholz et al.</Paragraph>
    <Paragraph position="1"> (1999), Soon et al. (2001)).</Paragraph>
    <Paragraph position="2"> In this paper we address the problem of aggregating the outputs of classi ers solving different NLP tasks. We compare pipeline-based processing with discrete optimization modeling used in the eld of computer vision and image recognition (Kleinberg &amp; Tardos, 2000; Chekuri et al., 2001) and recently applied in NLP by Roth &amp; Yih (2004), Punyakanok et al. (2004) and Althaus et al. (2004). Whereas Roth and Yih used optimization to solve two tasks only, and Punyakanok et al. and Althaus et al. focused on a single task, we propose a general formulation capable of combining a large number of different NLP tasks. We apply the proposed model to solving numerous tasks in the generation process and compare it with two pipeline-based systems.</Paragraph>
    <Paragraph position="3"> The paper is structured as follows: in Section 2 we discuss the use of classi ers for handling NLP tasks and point to the limitations of pipeline processing.</Paragraph>
    <Paragraph position="4"> In Section 3 we present a general discrete optimization model whose application in NLG is described in Section 4. Finally, in Section 5 we report on the experiments and evaluation of our approach.</Paragraph>
  </Section>
class="xml-element"></Paper>