<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-1046">
  <Title>Aggregation via Set Partitioning for Natural Language Generation</Title>
  <Section position="8" start_page="364" end_page="365" type="concl">
    <SectionTitle>
7 Conclusions and Future Work
</SectionTitle>
    <Paragraph position="0"> In this paper we have presented a novel data-driven method for aggregation in the context of natural language generation. A key aspect of our approach is the use of global inference for finding aggregations that are maximally consistent and coherent. We have formulated our inference problem as an integer linear program and shown experimentally that it out-performs a baseline clustering model by a wide margin. Beyond generation, the approach holds promise for other NLP tasks requiring the accurate partitioning of items into equivalence classes (e.g., coreference resolution).</Paragraph>
    <Paragraph position="1">  Currently, semantic grouping is carried out in our model sequentially. First, a local classifier learns the similarity of entity pairs and then ILP is employed to infer a valid partitioning. Although such a model has advantages in the face of sparse data (recall that we used a relatively small training corpus of 300 documents) and delivers good performance, it effectively decouples learning from inference. An appealing future direction lies in integrating learning and inference in a unified global framework. Such a framework would allow us to incorporate global constraints directly into the learning process.</Paragraph>
    <Paragraph position="2"> Another important issue, not addressed in this work, is the interaction of our aggregation method with content selection and surface realization. Using an ILP formulation may be an advantage here since we could use feedback (in the form of constraints) from other components and knowlegde sources (e.g., discourse relations) to improve aggregation or indeed the generation pipeline as a whole (Marciniak and Strube, 2005).</Paragraph>
  </Section>
class="xml-element"></Paper>