This paper presents an implemented system for recognizing the occurrence of events described by simple spatial-motion verbs in short image sequences. The semantics of these verbs is specified with event-logic expressions that describe changes in the state of force-dynamic relations between the participants of the event. An efficient finite representation is introduced for the infinite sets of intervals that occur when describing liquid and semi-liquid events. Additionally, an efficient procedure using this representation is presented for inferring occurrences of compound events, described with event-logic expressions, from occurrences of primitive events. Using force dynamics and event logic to specify the lexical semantics of events allows the system to be more robust than prior systems based on motion profile. 1.

This paper describes an implemented computer program that recognizes the occurrence of simple spatial motion events in simulated video input. The program receives an animated line-drawing as input and produces as output a semantic representation of the events occurring in that animation. This paper suggests that the notions of support, contact, and attachment are crucial to specifying many simple spatial motion event types and presents a logical notation for describing classes of events that incorporates such notions as primitives. It then suggests that the truth values of such primitives can be recovered from perceptual input by a process of counterfactual simulation, predicting the effect of hypothetical changes to the world on the immediate future. Finally, it suggests that such counterfactual simulation is performed using knowledge of naive physical constraints such as substantiality, continuity, gravity, and ground plane. This paper describes the algorithms that incorporate these ideas in the program and illustrates the operation of the program on sample input.

This paper proposes a solution to the computational task of extracting temporal information from simple declarative sentences based on separating temporal analysis into distinct tasks, each of which has access to a selected portion of the temporal input. The ultimate goal is to represent temporal information as explicitly as possible at each stage of analysis in order to provide the appropriate information for the next stage. Because the representations are constructed incrementally, it is important that they should be explicit about what has been derived so far, yet sufficiently noncommittal to avoid conflicting with subsequent processing

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.

this paper is to present a particular type of lexicon, elaborated within a formal theory of natural language called Meaning-Text Theory (MTT). This theory puts strong emphasis on the development of highly structured lexica. Computational linguistics does of course recognize the importance of the lexicon in language processing. However, MTT probably goes further in this direction than various we!l-known approaches within computational linguistics; it assigns to the lexicon a central place, so that the rest of linguistic description is supposed to pivot around the lexicon. It is in this spirit that MTT views the model of natural language: the Meaning-Text Model, or MTM. It is believed that a very rich lexicon presenting individual information about iexemes in a consistent and detailed way facilitates the general task of computational linguistics by dividing it into two more or less autonomous subtasks: a linguistic and a computational one. The MTM lexicon, embodying a vast amount of linguistic information, can be used in different computational applications. We will present here a short outline of the lexicon in question as well as of its interaction with other components of the MTM, with special attention to computational implications of the Meaning-Text Theory

NUMERICAL -- REAL -- PHYSICAL -- NON-STATIONARY -- COLLECTIVE TEMPORAL -- RELATIONAL -- EVENT -- Table 1.

This paper describes results of a dynamic model of aspectual composition that demonstrates how features necessary for planning and controlling actions can also motivate and ground simple analyses of a number of aspectual phenomena. A novel feature of the model is an active computational representation for verb semantics called x-schemas, an extension of the Petri net formalism that can encode goals, resources and other features affecting aspect. Vexing problems of aspectual composition lend themselves to simple analyses in terms of the context-sensitive interaction between verb-specific x-schemas and a controller x-schema that captures important regularities in the evolution of events. The resulting x-schemas can be elaborated and constrained by such factors as tense, temporal modifiers, nominals and pragmatic context, providing a rich representation that supports simulative inference in language understanding. Introduction Since Vendler's seminal paper (1967), the co...

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...

In this work, which is intended to form a very general backdrop for considering the semantics of generic sentences, we are going to examine some basic assumptions about how work on generics is to proceed, and what basic, empirical issues need to be accounted for by any adequate theory of generic meaning. There are two generally opposed perspectives on how generic sentences can be true or false. One view takes induction as its primary model and attempts to understand generics in terms of the inductive process. The other perspective takes rules and regulations (e.g. of games or legally-regulated activity) as its primary model, and seeks to understand generics in those terms. Our present purposes are to review the primary features of the opposition, to evaluate the strengths and weaknesses of each, and to discuss reasons for choosing one over the other. The discussion will be cast in terms of a general opposition, though one must eventually allow for mixed or intermediate positions. Work on the semantics of generics, however, tends to take one point of view or the other as its guiding feature, and so considering the opposition in this unqualified form has some merit. Before proceeding, though, I'd first like to get a couple of matters out of the way. First, I will take it for granted that I know what a generic sentence is--any sentence expressing a