<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-0130">
  <Title>Chinese Named Entity Recognition with Conditional Probabilistic Models</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> At the third International Chinese Language Processing Bakeoff, we participated in the closed test in the Named Entity Recognition (NER) task using the MSRA corpus and the CITYU corpus.</Paragraph>
    <Paragraph position="1"> The named entity types include person, place, and organization. The training data consist of texts that are segmented into words with names of people, places, and organizations labeled. And the testing data consist of un-segmented Chinese texts, one sentence per line.</Paragraph>
    <Paragraph position="2"> There are many well known models for English named recognition, among which Conditional Random Fields (Lafferty et al. 2001) and maximum entropy models (Berger et al. 2001) have achieved good performance in English in CoNLL NER tasks. To understand the performance of these two models on Chinese, we both models to Chinese NER task on MSRA data and CITYU data.</Paragraph>
  </Section>
class="xml-element"></Paper>