Teaching computers to understand the meaning of natural language text has long been an important goal for Artificial Intelligence. The focus of my work is on the interpretation of descriptions of visual scenes such as ‘A man is sitting on a chair and using the computer’. One application of this research is the automatic generation of 3D scenes (Coyne and Sproat 2001), such as the one in Figure ...

Semantic analysis of text is often based on semantic roles drawn from a small, closed set. The set of roles describing relationships between a verb and its arguments within a clause are cases. This report assesses the cases used in the TANKA project (Text ANalysis for Knowledge Acquisition) according to the distribution of the words and syntactic constituents that mark them. The definitions of ...

Large-scale data resources needed for progress toward natural language understanding are not yet widely available and typically require considerable expense and expertise to create. This paper addresses the problem of developing scalable approaches to annotating semantic frames and explores the viability of crowdsourcing for the task of frame disambiguation. We present a novel supervised crowds...

Frame semantics is a linguistic theory which is currently gaining ground. The creation of lexical entries for a large number of words presupposes the development of complex lexical acquisition techniques in order to identify the vocabulary for describing the elements of a 'frame'. In this paper, we show how a lexical-semantic database compiled on the basis of a bilingual (English-French) dictio...

I examine Gleitman’s (1990) arguments that children rely on a verb’s syntactic subcategorization frames to learn its meaning (e.g., they learn that see means ‘perceive visually’ because it can appear with a direct object, a clausal complement, or a directional phrase). First, Gleitman argues that the verbs cannot be learned by observing the situations in which they are used, because many verbs ...

It is well-established that (non-linguistic) categorization is driven by a functional demand of prediction. We suggest that prediction likewise may well play a role in motivating the learning of semantic generalizations about argument structure constructions. We report corpora statistics that indicate that the argument frame or construction has roughly equivalent cue validity as a predictor of ...