The application of the "back-propagation" learning algorithm to the task of determining the right set of features corresponding to the words in an input sentence is described. Features that are specific to particular nouns and verbs, that indicate whether a nominal constituent is singular or plural, definite or indefinite, and that…

Although Eskimo languages are commonly characterized as displaying rather "free" word order compared to major western European languages, West Greenlandic (WG) has a clearly dominant, pragmatically neutral ordering pattern. It is argued that WG behaves more like Slavic languages. (Contains 36 references.) (LB)

A computer-based artificial neural network (ANN) that learns to classify sentences in a text as important or unimportant is described. The program is designed to select the sentences that are important enough to be included in composition of an abstract of the text. The ANN is embedded in a conventional symbolic environment consisting of…

Discusses the relative merits of feature versus model based semantics for the interpretation of verb phrases in English, French, and German. The article concludes that the simplicity afforded by features is offset by the depth of analysis achieved with event models that are additionally able to support a sophisticated approach to machine…

The encoding of Swedish syntactic information in a study of linguistic data processing is described in detail. The choice of syntactic variables and classification criteria, illustrated with examples, is also discussed. In addition, uses of the coding for contrasting languages, as in this study's comparison of Swedish, Finnish, and English word…