摘要：By using the world's linguistic diversity, the study of meaning can be transformed from an introspective inquiry into a subject of empirical investigation. For this to be possible, the notion of meaning has to be operationalized by defining the meaning of an expression as the collection of all contexts in which the expression can be used. Under this definition, meaning can be empirically investigated by sampling contexts. A semantic map is a technique to show the relations between such sampled contextual occurrences. Or, formulated more technically, a semantic map is a visualization of a metric on contexts sampled to represent a domain of meaning. Or, put more succinctly, a semantic map is a metric on meaning. To establish such a metric, a notion of (dis)similarity is needed. The similarity between two meanings can be empirically investigated by looking at their encoding in many different languages. The more similar these encodings, in language after language, the more similar the contexts. So, to investigate the similarity between two contextualized meanings, only judgments about the similarity between expressions within the structure of individual languages are needed. As an example of this approach, data on cross-linguistic variation in inchoative/causative alternations from Haspelmath (1993) is reanalyzed.
