<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-0108">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics Cluster-based Language Model for Sentence Retrieval in Chinese Question Answering</Title>
  <Section position="6" start_page="62" end_page="62" type="concl">
    <SectionTitle>
5 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> The input of a question answering system is natural language question which contains richer information than the query in traditional document retrieval. Such richer information can be used in each module of question answering system. In this paper, we presented a novel cluster-based language model for sentence retrieval in Chinese question answering which combines the sentence model, the cluster/topic model and the collection model.</Paragraph>
    <Paragraph position="1"> For sentence clustering, we presented two approaches that are One-Sentence-Multi-Topics and One-Sentence-One-Topic respectively. The experimental results showed that the proposed cluster-based language model could improve the performances of sentence retrieval in Chinese question answering significantly.</Paragraph>
    <Paragraph position="2"> However, we only conduct sentence clustering for questions, which have the property that their answers are named entities in this paper. In the future work, we will focus on all other type questions and improve the performance of the sentence retrieval by introducing the structural, syntactic and semantic information into language model.</Paragraph>
  </Section>
class="xml-element"></Paper>