Fourteen linguistically-motivated numeri- cal indicators are evaluated for their abil- ity to categorize verbs as either states or events. The values for each indicator are computed automatically across a corpus of text. To improve classification performance, machine learning techniques are employed to combine multiple indicators. Three machine learning methods are compared for this task: decision tree induction, a genetic algorithm, and log-linear regres- sion.

Verbal and compositional lexical aspect provide the underlying temporal structure of events. Knowledge of lexical aspect, e.g.. (a)telicity, is therefore required for interpreting event sequences in dis- course (Dowry, 1986; Moens and Steed- man, 1988; Passoneau, 1988), interfacing to temporal databases (Androutsopoulos, 1996), processing temporal modifiers (Antonisse, 1994), describing allowable alternations and their semantic effects (Resnik, 1996; Tenny, 1994), and selecting tense and lexical items for natural language generation ((Dorr and Olsen, 1996; Klavans and Chodorow, 1992), cf. (Slobin and Bocaz, 1988)). We show that it is possible to represent lexical aspect--both verbal and compositional--on a large scale, using Lexical Conceptual Structure (LCS) representations of verbs in the classes cat- aloged by Levin (1993). Ve show how proper consideration of these universal pieces of verb meaning may be used to refine lexical representations and derive a range of meanings from combinations of LCS representations. A single algorithm may therefore be used to determine lexical aspect classes and features at both verbal and sentence levels. Finally, we illustrate how knowledge of lexical aspect facilitates the interpretation of events in NLP appli- cations.

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 com- pletedness (i.e., tellcity), over unrestricted sets of verbs from two corpora. Several of these indicators have not previously been discovered to correlate with aspect.

In this paper, I demonstrate that verbs can be disambiguated according to aspect by rules that examine the WordNet category of the direct object. First, when evaluated over a corpus of medical reports, I show that WordNet categories correlate with aspectual class. Then, I develop a rule for distinguishing between stative and event occurrences of have by the WordNet category of the direct object. This rule, which is motivated by both linguistic and statistical analysis, is evaluated over an unrestricted set of nouns. I also show that WordNet categories improve a system that performs aspectual classification with linguistically-based numerical indicators. 1 Introduction The verb have is semantically ambiguous. It can denote a possessive relationship, as in, I had a car, or endow a quality, as in, I had anxiety. Further, have can describe an act of creation, as in, I had a baby, or an undertaking, as in, I had lunch. Broadly, all uses of have either denote a state, i.e., a situation t...

: Verbal and compositional lexical aspect provide the underlying temporal structure of events. Knowledge of lexical aspect, e.g., (a)telicity, is therefore required for interpreting event sequences in discourse (Dowty, 1986; Moens and Steedman, 1988; Passoneau, 1988), interfacing to temporal databases (Androutsopoulos, 1996), processing temporal modifiers (Antonisse, 1994), describing allowable alternations and their semantic effects (Resnik, 1996; Tenny, 1994), and selecting tense and lexical items for natural language generation ((Dorr and Olsen, 1996; Klavans and Chodorow, 1992), cf. (Slobin and Bocaz, 1988)). We show that it is possible to represent lexical aspect---both verbal and compositional---on a large scale, using Lexical Conceptual Structure (LCS) representations of verbs in the classes cataloged by Levin (1993). We show how proper consideration of these universal pieces of verb meaning may be used to refine lexical representations and derive a range of meanings from combin...

In this paper, I demonstrate that verbs can be disambiguated according to aspect by rules that ernine the WordNet category of the direct object. First, when evaluated over a corpus of medical reports, I show that WordNet categories correlate with aspectual class. Then, I develop a rule for distinguishing between starire and event occurrences of have by the WordNet category of the direct object. This rule, which is motivated by both linguistic and statistical analysis, is evaluated over an unrestricted set of nouns. I also show that WordNet categories improve a system that performs aspectual classification with lingnistically-based numerical indicators.

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.

In this paper, I demonstrate that verbs can be disambiguated according to aspect by rules that examine the WordNet category of the direct object. First, when evaluated over a corpus of medical reports, I show that WordNet categories correlate with aspectual class. Then, I develop a rule for distinguishing between stative and event occurrences of have by the WordNet category of the direct object. This rule, which is motivated by both linguistic and statistical analysis, is evaluated over an unrestricted set of nouns. I also show that WordNet categories improve a system that performs aspectual classification with linguistically-based numerical indicators.

In this paper, I demonstrate that verbs can be disambiguated according to aspect by rules that examine the WordNet category of the direct object. First, when evaluated over a corpus of medical reports, I show that WordNet categories correlate with aspectual class. Then, I develop a rule for distinguishing between stative and event occurrences of have by the WordNet category of the direct object. This rule, which is motivated by both linguistic and statistical analysis, is evaluated over an unrestricted set of nouns. I also show that WordNet categories improve a system that performs aspectual classification with linguistically-based numerical indicators. 1

Fourteen linguistically-motivated numerical indicators are evaluated for their ability to categorize verbs as either states or events. The values for each indicator are computed automatically across a corpus of text. To improve classification performance, machine learning techniques are employed to combine multiple indicators. Three machine learning methods are compared for this task: decision tree induction, a genetic algorithm, and log-linear regression. 1