Automatic Acquisition of the Lexical Semantics of Verbs from Sentence Frames

This paper presents a computational model of verb acquisition which uses what we will call the principle of structured overeommitment to eliminate the need for negative evidence. The learner escapes from the need to be told that certain possibilities cannot occur (i.e., are "ungrammatical") by one simple expedient: It assumes that all properties it has observed are either obligatory or forbidden until it sees otherwise, at which point it decides that what it thought was either obligatory or forbidden is merely optional. This model is built upon a classification of verbs based upon a simple three-valued set of features which represents key aspects of a verb's syntactic structure, its predicate/argument structure, and the mapping between them. 1 I N T R O D U C T I O N The problem of how language is learned is perhaps the most difficult puzzle in language understanding. It is necessary to understand learning in order to understand how people use and organize language. To build truly robust natural language systems, we must ultimately understand how to enable our systems to learn new forms themselves. Consider the problem of learning new lexical items in context. To take a specific example, how is it that a child can learn the difference between the verbs look and see (inspired by Landau and Gleitman(1985) )? They clearly have similar core meanings, namely ~perceive by sight". One initially attractive and widely-held hypothesis is that *This work was partially supported by the DARPA grant N00014-85-K0018, and Alto grant DAA29-84-90027. The authors also wish to thank Beth Levin and the anonymotm reviewers of this paper for many helpful comments. We ~ b~efit~l greatly from disctumion of issues of verb acquisition in children with Lila Gleitman. word meaning is learned directly by observation of the surrounding non-linguistic context. While this hypothesis ultimately only begs the question, it also runs into immediate substantive difficulties here, since there is usually looking going on at the same time as seeing and vice versa. But how can one learn that these verbs differ in that look is an active verb and see is stative? This difference, although difficult to observe in the environment, is clearly marked in the different syntactic frames the two verbs are found in. For example, see, being a stative perception verb, can take a sentence complement: (1) John saw that Mary was reading.