Pii: S0364-0213(01)00034-9
نویسنده
چکیده
In Latent Semantic Analysis (LSA) the meaning of a word is represented as a vector in a high-dimensional semantic space. Different meanings of a word or different senses of a word are not distinguished. Instead, word senses are appropriately modified as the word is used in different contexts. In N-VP sentences, the precise meaning of the verb phrase depends on the noun it is combined with. An algorithm is described to adjust the meaning of a predicate as it is applied to different arguments. In forming a sentence meaning, not all features of a predicate are combined with the features of the argument, but only those that are appropriate to the argument. Hence, a different “sense” of a predicate emerges every time it is used in a different context. This predication algorithm is explored in the context of four different semantic problems: metaphor interpretation, causal inferences, similarity judgments, and homonym disambiguation. © 2001 Cognitive Science Society, Inc. All rights reserved.
منابع مشابه
Eye scanpaths during visual imagery reenact those of perception of the same visual scene
Eye movements during mental imagery are not epiphenomenal but assist the process of image generation. Commands to the eyes for each fixation are stored along with the visual representation and are used as spatial index in a motor-based coordinate system for the proper arrangement of parts of an image. In two experiments, subjects viewed an irregular checkerboard or color pictures of fish and we...
متن کاملPii: S0364-0213(00)00037-9
In this article we present a new experimental paradigm: comparative visual search. Each half of a display contains simple geometrical objects of three different colors and forms. The two displayhalves are identical except for one object mismatched in either color or form. The subject’s task is to find this mismatch. We illustrate the potential of this paradigm for investigating the underlying c...
متن کامل