<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-1007">
  <Title>Frame Semantic Enhancement of Lexical-Semantic Resources</Title>
  <Section position="6" start_page="63" end_page="64" type="concl">
    <SectionTitle>
5 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> SemFrame's output can be used to enhance lexical-semantic resources in various ways. For example, WordNet has recently incorporated new relationship types, some of which touch on frame semantic relationships. But frame semantic relationships are as yet only implicit in WordNet; not all morphological derivation relationships, for example, operate within a frame. Should WordNet choose to reflect frame semantic relationships, SemFrame would provide a useful point of departure, since the verb framesets, frame names, and frame slots are all already expressed as WordNet synsets.</Paragraph>
    <Paragraph position="1"> SemFrame can also add to FrameNet. The extensive human effort that has gone into FrameNet is overwhelmingly evident in the quality of its frame structures (and attendant annotations). SemFrame is unlikely ever to compete with FrameNet on this score. However, SemFrame has identified frames not recognized in FrameNet, e.g., SemFrame's SOILING frame. SemFrame has likewise identified lexical units appropriate to FrameNet frames that have not yet been incorporated into FrameNet, e.g., stick to, stick with, and abide by in the COMPLIANCE / CONFORMITY frame. These contributions would add as well to the semantic representations in PropBank. Since identifying frames and their evoking lexical units from scratch requires more effort than assessing the general quality of proposed frames and lexical units--indeed, since there is currently no other systematic way in which to identify either a universal set of semantic frames or the set of lexical items that evoke a frame--SemFrame's ability to propose new frames and new evoking lexical units constitutes a major contribution to the development of lexical-semantic resources.</Paragraph>
    <Paragraph position="2"> SemFrame's current results might themselves be enhanced by considering data from other parts of speech. For instance, at present SemFrame bases all its frames on verb framesets, but some FrameNet frames list only adjectives as evoking lexical units.</Paragraph>
    <Paragraph position="3"> At the same time, potentially more can be done in associating verb synsets with frames: Only one-third of WordNet's verb synsets are now included in SemFrame's output. Some of those not now included evoke none of SemFrame's current frames, but some do and have not yet been recognized. Ways of establishing hierarchical and compositional relationships among frames should also be investigated.</Paragraph>
    <Paragraph position="4"> The above suggestions for enhancing SemFrame notwithstanding, major progress in improving SemFrame awaits incorporation of corpus data. Relying on data from lexical resources has contributed to SemFrame's precision, but the data sparseness bottleneck that SemFrame faces is nonetheless real.</Paragraph>
    <Paragraph position="5"> On the basis of the lexical resource data used, verb synsets are related on average to only 5 nouns, many of which closely reflect the participant structure of the corresponding frame. However, it is not uncommon for specific elements of the participant structure to go unrepresented, and any nouns in the dataset that are not particularly reflective of the participant structure carry far too much weight amidst such a paucity of data.</Paragraph>
    <Paragraph position="6"> In contrast, the number of nouns that co-occur with a verb in a corpus may be orders of magnitude greater.13 But the nouns in a corpus are less likely to reflect closely the participant structure of the corresponding frame; many more nouns are thus likely to be needed. Furthermore, word sense disambiguation will be required to assign to a frame only those nouns corresponding to an appropriate sense of the verb.14 We are optimistic, however, that the presence of additional corpus data will help fill in frame element gaps arising from the sparseness of lexical resource data and can also be used to help reduce the impact of nouns from lexical resource data that are not representative of a frame's participant structure.</Paragraph>
    <Paragraph position="7"> Coupled with subject-specific resources, the analysis of corpus data may then lead to the development 13We are investigating two levels of noun-verb cooccurrence. The first counts co-occurrences of all nouns and verbs appearing within the same paragraph of newswire texts. The second counts only those nouns related to verbs as their subjects, direct objects, indirect objects, or as objects of prepositional phrases that modify the verb.</Paragraph>
    <Paragraph position="8"> 14We make the simplifying assumption that if a noun occurs with some reasonable percentage of the verbs within a frameset, the desired verb sense is in play.</Paragraph>
    <Paragraph position="9">  of subject-specific frame inventories. Such inventories can in turn inform such knowledge-intensive applications as information retrieval, information extraction, and question answering.</Paragraph>
  </Section>
class="xml-element"></Paper>