Learning Word Meanings From Examples

This paper describes work in progress on a computer program that uses syntactic constraints to derive the meanings of verbs from an analysis of simple English example stories. The central idea is an extension of Winston's (Winston 1975) program that learned the structural descriptions of blocks world scenes. In the new research, English verbs take the place of blocks world objects like ARCH and TOWKR, with frame-based descriptions of causal relationships serving as the structural descriptions. Syntactic constraints derived from the parsing of story plots arc used to drive an analogical matching procedure. Analogical matching gives a way to compare descriptions of known words to unknown words. The "meaning" of a new verb is learned by matching pan of the causal network description of a story precis containing the unknown word to a set of such descriptions derived from similar stories that contain only known words. The best match forges an assignment between objects and relations such that the unknown veib is matched to a known verb, with the assignment being guided by syntactic constraints. The causal network surrounding the unknown item is then used as a scaffolding to construct a network representing the use of the novel word in a particular context. Words (and their associated stories) that are "best matches" are grouped together into a similarity network, according to the match score. I W O R D ACQUISITION A N D DEFINITIONS This paper describes an analogical matching system that attempts to learn the causal descriptions of new words. The end result is that there arc no "definitions" in the sense of necessary and sufficient conditions determining word meanings; rather, what is output is an interconnected set of descriptions of the actual use of words in context (under a particular theory of "context", namely, causal network structure). The use of analogical matching here should not be viewed as a necessary ingredient of the learning system, but rather one way to represent a program's knowledge about the world. In other words, story plots serve as a proxy for systematic understanding of how the world works, and by matching stories the program can determine that a novel situation will work like an old one. The word learning program is also embedded into a larger system that can acquire new syntactic rules for Knglish, as described in (Berwick 1979 198