Corpus-Based Linguistic Indicators for Aspectual Classification

Fourteen indicators that measure the frequency of lexico-syntactic phenomena linguistically related to aspectual class are applied to aspectual classification. This group of indicators is shown to improve classification performance for two aspectual distinctions, stativity and completedness (i.e., telicity), over unrestricted sets of verbs from two corpora. Several of these indicators have not previously been discovered to correlate with aspect. 1 I n t r o d u c t i o n Aspectual classification maps clauses to a small set of primitive categories in order to reason about time. For example, events such as, "You called your father," are distinguished from states such as, "You resemble your father." These two high-level categories correspond to primitive distinctions in many domains, e.g., the distinction between procedure and diagnosis in the medical domain. Aspectual classification further distinguishes events according to completedness (i.e., telicity), which determines whether an event reaches a culmination point in t ime at which a new state is introduced. For example, "I made a fire" is culminated, since a new state is introduced something is made, whereas, "I gazed at the sunset" is non-culminated. Aspectual classification is necessary for interpreting temporal modifiers and assessing temporal entailments (Vendler, 1967; Dowty, 1979; Moens and Steedman, 1988; Dorr, 1992), and is therefore a necessary component for applications that perform certain natural language interpretation, natural language generation, summarization, information retrieval, and machine translation tasks. Aspect introduces a large-scale, domaindependent lexical classification problem. Although an aspectual lexicon of verbs would suffice to classify many clauses by their main verb only, a verb's primary class is often domaindependent (Siegel, 1998b). Therefore, it is necessary to produce a specialized lexicon for each domain. Most approaches to automatically categorizing words measure co-occurrences between open-class lexical items (Schfitze, 1992; Hatzivassiloglou and McKeown, 1993; Pereira et al., 1993). This approach is limited since cooccurrences between open-class lexical items is sparse, and is not specialized for particular semantic distinctions such as aspect. In this paper, we describe an expandable framework to classify verbs with linguisticallyspecialized numerical indicators. Each linguistic indicator measures the frequency of a lexicosyntactic marker, e.g. the perfect tense. These markers are linguistically related to aspect, so the indicators are specialized for aspectual classification in particular. We perform an evaluation of fourteen linguistic indicators over unrestricted sets of verbs from two corpora. When used in combination, this group of indicators is shown to improve classification performance for two aspectual distinctions: stativity and completedness. Moreover, our analysis reveals a predictive value for several indicators that have not previously been discovered to correlate with aspect in the linguistics literature. The following section further describes aspect, and introduces linguistic insights that are exploited by linguistic indicators. The next section describes the set of linguistic indicators evaluated in this paper. Then, our experimental method and results are given, followed by a discussion and conclusions.