<?xml version="1.0" standalone="yes"?>
<Paper uid="P01-1032">
  <Title>Mapping Lexical Entries in a Verbs Database to WordNet Senses</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Our goal is to map entries in a lexical database of 4076 English verbs automatically to Word-Net senses (Miller and Fellbaum, 1991), (Fellbaum, 1998) to support such applications as machine translation and cross-language information retrieval. For example, the verb drop is multiply ambiguous, with many potential translations in Spanish: bajar, caerse, dejar caer, derribar, disminuir,echar, hundir, soltar, etc. The database specifies a set of interpretations for drop, depending on its context in the source-language (SL). Inclusion of WordNet senses in the database enables the selection of an appropriate verb in the target language (TL). Final selection is based on a frequency count of WordNet senses across all classes to which the verb belongs--e.g., disminuir is selected when the WordNet sense corresponds to the meaning of drop in Prices dropped.</Paragraph>
    <Paragraph position="1"> Our task differs from standard word sense disambiguation (WSD) in several ways. First, the words to be disambiguated are entries in a lexical database, not tokens in a text corpus. Second, we take an &amp;quot;all-words&amp;quot; rather than a &amp;quot;lexical-sample&amp;quot; approach (Kilgarriff and Rosenzweig, 2000): All words in the lexical database &amp;quot;text&amp;quot; are disambiguated, not just a small number for which detailed knowledge is available. Third, we replace the contextual data typically used for WSD with information about verb senses encoded in terms of thematic grids and lexical-semantic representations from (Olsen et al., 1997). Fourth, whereas a single word sense for each token in a text corpus is often assumed, the absence of sentential context leads to a situation where several WordNet senses may be equally appropriate for a database entry.</Paragraph>
    <Paragraph position="2"> Indeed, as distinctions between WordNet senses can be fine-grained (Palmer, 2000), it may be unclear, even in context, which sense is meant.</Paragraph>
    <Paragraph position="3"> The verb database contains mostly syntactic information about its entries, much of which applies at the class level within the database. Word-Net, on the other hand, is a significant source for information about semantic relationships, much of which applies at the &amp;quot;synset&amp;quot; level (&amp;quot;synsets&amp;quot; are WordNet's groupings of synonymous word senses). Mapping entries in the database to their corresponding WordNet senses greatly extends the semantic potential of the database.</Paragraph>
  </Section>
class="xml-element"></Paper>