<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-2007">
  <Title>Towards a Semantic Classi cation of Spanish Verbs Based on Subcategorisation Information</Title>
  <Section position="5" start_page="0" end_page="0" type="concl">
    <SectionTitle>
4 Conclusions and Future Work
</SectionTitle>
    <Paragraph position="0"> We have presented a series of experiments that use an unsupervised learning method to classify Spanish verbs into semantic classes based on subcategorisation information. We apply well-known techniques that have been developed for the English language to Spanish, con rming that empirical methods can be re-used through languages without substantial changes in the methodology. In the task of acquiring subcategorisation frames, we achieve state of the art results. On the contrary, the task of inducing semantic classes from syntactic information using a clustering algorithm leaves room for improvement. The future work for this task goes on two directions.</Paragraph>
    <Paragraph position="1"> On the one hand, the theoretical basis of the manual verb classi cation suggests that, although the syntactic behaviour of verbs is an important criteria for a semantic classi cation, other properties of the verbs should be taken into account. Therefore, the description of verbs could be further enhanced with features that re ect on meaning components and event structure. The incorporation of name entity recognition in the experiments reported here is a rst step in this direction, but it is probably a too sparse feature in the data to make any significant contributions. The event structure of predicates could be statistically approximated from text by grasping the aspect of the verb. The aspect of the verbs could, in turn, be approximated by developing features that would consider the usage of certain tenses, or the presence of certain types of adverbs that imply a restriction on the aspect of the verb. Adverbs such as suddenly , continuously , often , or even adverbial sentences such as every day give information on the event structure of predicates. As they are a closed class of words, a typology of adverbs could be established to approximate the event structure of the verb (Esteve Ferrer and Merlo, 2003).</Paragraph>
    <Paragraph position="2"> On the other hand, an observation of the verb clusters output by the algorithm suggests that they are intuitively more plausible than what the evaluation measures indicate. For the purposes of possible applications, a hard clustering of verbs does not seem to be necessary, especially when even manually constructed classi cations adopt arbitrary decisions and do not agree with each other: knowing which verbs are semantically similar to each other in a more fuzzy way might be even more useful. For this reason, a new approach could be envisaged for this task, in the direction of the work by (Weeds and Weir, 2003), by building rankings of similarity for each verb. For the purpose of evaluation, the gold standard classi cation could also be organised in the form of similarity rankings, based on the distance between the verbs in the hierarchy. Then, the rankings for each verb could be evaluated. The two directions appointed here, enriching the verb descriptions with new features that grasp other properties of the verbs, and envisaging a similarity ranking of verbs instead of a hard clustering, are the next steps to be taken for this work.</Paragraph>
  </Section>
class="xml-element"></Paper>