<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1014">
  <Title>Meaningful Clustering of Senses Helps Boost Word Sense Disambiguation Performance</Title>
  <Section position="3" start_page="0" end_page="105" type="intro">
    <SectionTitle>
1 Introduction
Word Sense Disambiguation (WSD) is undoubt-
</SectionTitle>
    <Paragraph position="0"> edly one of the hardest tasks in the field of Natural Language Processing. Even though some recent studies report benefits in the use of WSD in specific applications (e.g. Vickrey et al. (2005) and Stokoe (2005)), the present performance of the best ranking WSD systems does not provide a sufficient degree of accuracy to enable real-world, language-aware applications.</Paragraph>
    <Paragraph position="1"> Most of the disambiguation approaches adopt the WordNet dictionary (Fellbaum, 1998) as a sense inventory, thanks to its free availability, wide coverage, and existence of a number of standard test sets based on it. Unfortunately, WordNet is a fine-grained resource, encoding sense distinctions that are often difficult to recognize even for human annotators (Edmonds and Kilgariff, 1998).</Paragraph>
    <Paragraph position="2"> Recent estimations of the inter-annotator agreement when using the WordNet inventory report figures of 72.5% agreement in the preparation of the English all-words test set at Senseval-3 (Snyder and Palmer, 2004) and 67.3% on the Open Mind Word Expert annotation exercise (Chklovski and Mihalcea, 2002). These numbers lead us to believe that a credible upper bound for unrestricted fine-grained WSD is around 70%, a figure that state-of-the-art automatic systems find it difficult to outperform. Furthermore, even if a system were able to exceed such an upper bound, it would be unclear how to interpret such a result.</Paragraph>
    <Paragraph position="3"> It seems therefore that the major obstacle to effective WSD is the fine granularity of the Word-Net sense inventory, rather than the performance of the best disambiguation systems. Interestingly, Ng et al. (1999) show that, when a coarse-grained sense inventory is adopted, the increase in inter-annotator agreement is much higher than the reduction of the polysemy degree.</Paragraph>
    <Paragraph position="4"> Following these observations, the main question that we tackle in this paper is: can we produce and evaluate coarse-grained sense distinctions and show that they help boost disambiguation on standard test sets? We believe that this is a crucial research topic in the field of WSD, that could potentially benefit several application areas.</Paragraph>
    <Paragraph position="5"> The contribution of this paper is two-fold. First, we provide a wide-coverage method for clustering WordNet senses via a mapping to a coarse-grained sense inventory, namely the Oxford Dictionary of English (Soanes and Stevenson, 2003) (Section 2).</Paragraph>
    <Paragraph position="6"> We show that this method is well-founded and accurate with respect to manually-made clusterings (Section 3). Second, we evaluate the performance of WSD systems when using coarse-grained sense inventories (Section 4). We conclude the paper with an account of related work (Section 5), and some final remarks (Section 6).</Paragraph>
  </Section>
class="xml-element"></Paper>