<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2019">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics Constraint-based Sentence Compression An Integer Programming Approach</Title>
  <Section position="8" start_page="150" end_page="150" type="concl">
    <SectionTitle>
6 Conclusions and Future Work
</SectionTitle>
    <Paragraph position="0"> In this paper we have presented a novel method for automatic sentence compression. A key aspect of our approach is the use of integer programming for inferring globally optimal compressions in the presence of linguistically motivated constraints. We have shown that such a formulation allows for a relatively simple and knowledge-lean compression model that does not require parallel corpora or access to large-scale knowledge bases.</Paragraph>
    <Paragraph position="1"> Our results demonstrate that the IP model yields performance comparable to state-of-the-art without any supervision. We also observe signi cant performance gains when a small amount of training data is employed (50 parallel sentences). Beyond the systems discussed in this paper, the approach holds promise for other models using decoding algorithms for searching the space of possible compressions. The search process could be framed as an integer program in a similar fashion to our work here.</Paragraph>
    <Paragraph position="2"> We obtain our best results using a model whose objective function includes a signi cance score.</Paragraph>
    <Paragraph position="3"> The signi cance score relies mainly on syntactic and lexical information for determining whether a word is important or not. An appealing future direction is the incorporation of discourse-based constraints into our models. The latter would highlight topical words at the document-level instead of considering each sentence in isolation. Another important issue concerns the portability of the models presented here to other languages and domains. We plan to apply our method to languages with more exible word order than English (e.g., German) and more challenging spoken domains (e.g., meeting data) where parsing technology may be less reliable.</Paragraph>
  </Section>
class="xml-element"></Paper>