and use of gist, formulating this problem as a rational statistical inference. This leads us to a novel approach to semantic representation in which word meanings are represented in terms of a set of probabilistic topics. The topic model performs well in predicting word association and the effects

” of broad-coverage semantic representation (SR). It suggests mul-tiple desiderata for such representations, and then out-lines more than a dozen approaches to SR–some long-standing, and some more recent, providing quick char-acterizations, pros, cons, and some comments on imple-mentations.

This chapter deals with how word meaning is represented by speakers of a language, reviewing psychological perspectives on the representation of meaning. We start by outlining four key issues in the investigation of word meaning, then we introduce current theories of semantics and we end with a

ences in the semantic representation of concrete and abstract words can be explained in terms of disproportionate numbers of semantic predicates, is explored in two experiments. The results suggest that (1) the advantage shown by concrete words in terms of greater number of predicates is only

is simply represented as a collection of atomic diagram components, and it ends up with some data structure as a semantic representation of the diagram. The specification of the translation process mainly consists of two parts: the specification of spatial relationships between atomic diagram components

The question of how meaning might be acquired by young children and represented by adult speakers of a language is one of the most debated topics in cognitive science. Existing semantic representation models are primarily amodal based on information provided by the linguistic input despite ample

Semantic networks produced from human data have statistical properties that cannot be easily captured by spatial representations. We explore a probabilistic approach to semantic representation that explicitly models the probability with which words occur in different contexts, and hence captures

A popular tradition of studying semantic representation has been driven by the assumption that word meaning can be learned from the linguistic environment, despite ample evidence suggesting that language is grounded in perception and action. In this paper we present a comparative study of models

The event structure (aktionsart) is a widely discussed issue for the representation of verbal semantics in languages. However, there is still problems for the classification of verbs into state, activity, accomplishment, achievement and semelfactive. It is also not clear where are the differences

Abstract The subject of this paper is the quality of semantic vector representation with random projection under various conditions. The main effect we are watching is the size of the context in which words are observed. We are also interested in the stability of such representations since