<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-0706">
  <Title>A Comparison between Supervised Learning Algorithms for Word Sense Disambiguation*</Title>
  <Section position="7" start_page="34" end_page="35" type="concl">
    <SectionTitle>
5 Conclusions
</SectionTitle>
    <Paragraph position="0"> This work reports a comparative study of five ML algorithms for WSD, and provides some results on cross corpora evaluation and domain re-tuning.</Paragraph>
    <Paragraph position="1"> Regarding portability, it seems that the performance of supervised sense taggers is not guaranteed when moving from one domain to another (e.g. from a balanced corpus, such as BC, to an economic domain, such as WSJ).</Paragraph>
    <Paragraph position="2">  These results imply that some kind of adaptation is required for cross-corpus application. Consequently, it is our belief that a number of issues regarding portability, tuning, knowledge acquisition, etc., should be thoroughly studied before stating that the supervised M k paradigm is able to resolve a realistic WSD problem.</Paragraph>
    <Paragraph position="3"> Regarding the ML algorithms tested, kazyBoosting emerges as the best option, since it outperforms the other four state-of-the-art methods in all experiments. Furthermore, this algorithm shows better properties when tuned to new domains. Future work is planned for an extensive evaluation of kazyBoosting on the WSD task. This would include taking into account additional/alternative attributes, learning curves, testing the algorithm on other corpora, etc.</Paragraph>
  </Section>
class="xml-element"></Paper>