<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-2910">
  <Title>Can Human Verb Associations Help Identify Salient Features for Semantic Verb Classification?</Title>
  <Section position="3" start_page="0" end_page="69" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> There are a variety of manual semantic verb classi cations; major frameworks are the Levin classes (Levin, 1993), WordNet (Fellbaum, 1998), and FrameNet (Fontenelle, 2003). The different frameworks depend on different instantiations of semantic similarity, e.g. Levin relies on verb similarity referring to syntax-semantic alternation behaviour, WordNet uses synonymy, and FrameNet relies on situation-based agreement as de ned in Fillmore's frame semantics (Fillmore, 1982). As an alternative to the resource-intensive manual classi cations, automatic methods such as classi cation and clustering are applied to induce verb classes from corpus data, e.g. (Merlo and Stevenson, 2001; Joanis and Stevenson, 2003; Korhonen et al., 2003; Stevenson and Joanis, 2003; Schulte im Walde, 2003; Ferrer, 2004). Depending on the types of verb classes to be induced, the automatic approaches vary their choice of verbs and classi cation/clustering algorithm. However, another central parameter for the automatic induction of semantic verb classes is the selection of verb features.</Paragraph>
    <Paragraph position="1"> Since the target classi cation determines the similarity and dissimilarity of the verbs, the verb feature selection should model the similarity of interest. For example, Merlo and Stevenson (2001) classify 60 English verbs which alternate between an intransitive and a transitive usage, and assign them to three verb classes, according to the semantic role assignment in the frames; their verb features are chosen such that they model the syntactic frame alternation proportions and also heuristics for semantic role assignment. In larger-scale classi cations such as (Korhonen et al., 2003; Stevenson and Joanis, 2003; Schulte im Walde, 2003), which model verb classes with similarity at the syntax-semantics interface, it is not clear which features are the most salient. The verb features need to relate to a behavioural component (modelling the syntax-semantics interplay), but the set of features which potentially in uence the behaviour is large, ranging from structural syntactic descriptions and argument role llers to adverbial adjuncts. In addition, it is not clear how ne-grained the features should be; for example, how much information is covered by low-level window co-occurrence vs. higher-order syntactic frame llers?  In this paper, we investigate whether human associations to verbs can help us to identify salient verb features for semantic verb classes. We collected associations to German verbs in a web experiment, and hope that these associations represent a useful basis for a theory-independent semantic classi cation of the German verbs, assuming that the associations model a non-restricted set of salient verb meaning aspects. In a preparatory step, we perform an unsupervised clustering on the experiment verbs, as based on the verb associations. We validate the resulting verb classes (henceforth: assoc-classes) by demonstrating that they show considerable overlap with standard approaches to semantic verb classes, i.e. GermaNet and FrameNet. In the main body of this work, we compare the associations underlying the assoc-classes with standard corpus-based feature types: We check on how many of the associations we nd among the corpus-based features, such as adverbs, direct object nouns, etc.; we hypothesise that the more associations are found as instantiations in a feature set, the better is a clustering as based on that feature type. We assess our hypothesis by applying various corpus-based feature types to the experiment verbs, and comparing the resulting classes (henceforth: corpus-classes) against the assoc-classes. On the basis of the comparison we intend to answer the question whether the human associations help identify salient features to induce semantic verb classes, i.e. do the corpus-based feature types which are identi ed on the basis of the associations outperform previous clustering results? By applying the feature choices to GermaNet and FrameNet, we address the question whether the same types of features are salient for different types of semantic verb classes? In what follows, the paper presents the association data in Section 2 and the association-based classes in Section 3. In Section 4, we compare the associations with corpus-based feature types, and in Section 5 we apply the insights to induce semantic verb classes.</Paragraph>
  </Section>
class="xml-element"></Paper>