<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-2005">
  <Title>Exploiting Named Entity Taggers in a Second Language</Title>
  <Section position="3" start_page="25" end_page="25" type="relat">
    <SectionTitle>
2 Related Work
</SectionTitle>
    <Paragraph position="0"> There has been a lot of work on NER, and there is a remarkable trend towards the use of machine learning algorithms. Hidden Markov Models (HMM) are a common choice in this setting. For instance, Zhou and Su trained HMM with a set of attributes combining internal features such as gazetteer information, and external features such as the context of other NEs already recognized (Zhou and Su, 2002). (Bikel et al., 1997) and (Bikel et al., 1999) are other examples of the use of HMMs.</Paragraph>
    <Paragraph position="1"> Previous methods for increasing the coverage of hand coded systems include that of Borthwick, he used a maximum entropy approach where he combined the output of three hand coded systems with dictionaries and other orthographic information (Borthwick, 1999). He also adapted his system to perform NER in Japanese achieving impressive results. null Spanish resources for NER have been used previously to perform NER on a different language.</Paragraph>
    <Paragraph position="2"> Carreras et al. presented results of a NER system for Catalan using Spanish resources (Carreras et al., 2003a). They explored several methods for building NER for Catalan. Their best results are achieved using cross-linguistic features. In this method the NER system is trained on mixed corpora and performs reasonably well on both languages. Our work follows Carreras et al. approach, but differs in that we apply directly the NER system for Spanish to Portuguese and train a classifier using the output and the real classes.</Paragraph>
    <Paragraph position="3"> In (Petasis et al., 2000) a new method for automating the task of extending a proper noun dictionary is presented. The method combines two learning approaches: an inductive decision-tree classifier and unsupervised probabilistic learning of syntactic and semantic context. The attributes selected for the experiments include POS tags as well as morphological information whenever available.</Paragraph>
    <Paragraph position="4"> One work focused on NE recognition for Spanish is based on discriminating among different kinds of named entities: core NEs, which contain a trigger word as nucleus, syntactically simple weak NEs, formed by single noun phrases, and syntactically complex named entities, comprised of complex noun phrases. Ar'evalo and colleagues focused on the first two kinds of NEs (Ar'evalo et al., 2002). The method is a sequence of processes that uses simple attributes combined with external information provided by gazetteers and lists of trigger words. A context free grammar, manually coded, is used for recognizing syntactic patterns.</Paragraph>
  </Section>
class="xml-element"></Paper>