<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-0712">
  <Title>I I I I I I I I I I I I I I I Augmenting WordNet-like lexical resources with distributional evidence. An application-oriented perspective&amp;quot;</Title>
  <Section position="4" start_page="91" end_page="92" type="concl">
    <SectionTitle>
5. Conclusions
</SectionTitle>
    <Paragraph position="0"> Semantic similarity is not simply a relation between two words in isolation, but rather a relation between two words in their context. This context-sensitive view of semantic sLrnJlarity makes its identification more problematic. In principle, semantic similarity of words  can be captured in a number of different ways, ranging from their taxonomical relationships to their actual distribution in a corpus. It would be very difficult to argue that one such a way is more plausible than another; nonetheless, it should be observed that their practical utility in well-known interesting NLP applications can vary considerably.</Paragraph>
    <Paragraph position="1"> We noted that taxonomy-based measures of semantic similarity are to an extent inadequate, as they capture only some of the classificatory dimensions which play a relevant role in NIP applications. We showed that relevant similarities need to be grounded on the specific context to be processed (e.g.</Paragraph>
    <Paragraph position="2"> disambiguated, retrieved or summarised) and that different contexts call for different classificatory dimensions. Distributional evidence can be used to model this sort of context-sensitive multidimensional classification, so as to induce semantic associations between words that nonetheless belong to different places in a taxonomy. We also showed that distributionally-based semantic similarity has a considerable impact on crucial NLP tasks such as word sense disambiguation. All this provides evidence that WordNet-like lexical resources should strive to integrate taxonomical and distributional information, by combining both paradigmatic and syntagmatic dimensions.</Paragraph>
    <Paragraph position="3"> As already mentioned, Word,Net has a potential for doing that, through extended implementation of so-called pointers from nouns to verbs and from verbs to nouns, to represent functions, typical semantic preferences etc. Within the EuroWordNet project (LE24003), some steps in this direction have already been taken in developing multilingual WordNets for Dutch, Italian and Spanish. Among the additions to the original set of relations borrowed from WordNet 1.5, syntagmatic relations feature prominently: e.g., one finds verb-to-noun relations denoting the typical entities involved in a given event, or noun-to-verb relations referring to the typical events in which a given entity play a role (Alonge et al. forthcoming).</Paragraph>
    <Paragraph position="4"> This certainly provides the information needed to capture context-sensitive semantic similarities. We also showed that local inferential engines such as SENSE can demonstrably tap this type of information with the degree of flexibility, noise-tolerance and inputrelevance required, among others, by WSD.</Paragraph>
  </Section>
class="xml-element"></Paper>