A connectionist back-propagation net is trained to learn a mapping between verb forms (infinitive, imperative, present tense) and past tense forms. A back-propagation network requires that a one-to-one mapping exists between input and output. Since Swedish past tense is characterized by choice between weak and strong forms this proves a hard task for the net. Examples are: nypte/nöp ‘pinched’, tvang/tvingade ‘forced’, where there is no obvious reason for preferring one form over the other. The task is still worth doing since regularities emerge in the net over time. The performance of the connectionist model is analysed and compared to previous results.

This paper presents an overview of the first broad coverage grammatical description of Danish in a Typed Feature Structure (TFS) based unification formalism inspired by HPSG. These linguistic specifications encompass phenomena within inflectional morphology, phrase structure and predicate argument structure, and have been developed with a view to implementation. The emphasis on implementability and re-usability of the specifications has led to the adoption of a rather leaner formal framework than that underlying HPSG. However, the paper shows that the adoption of such a framework does not lead to a loss of expressibility, but in fact enables certain phenomena, such as the interface between morphology and syntax and local discontinuities, to be treated in a simple and elegant fashion.

Danish motion verbs provide a good candidate for testing the hypothesis of semantic determination on Danish, a hypothesis most recently discussed by Levin (1993) in her description of English verb classes and alternations. A set of core meaning components for motion verbs is identified and a taxonomy of Danish motion verbs is produced. With the basic assumption that a word's meaning determines its syntactic potential, this paper gives an account of the syntactic alternations that Danish motion verbs can undergo, and exposes a more or less transparent relation between their syntax and semantics.

The present paper is a discussion of the syntactic and semantic treatment of proper names in the generalized quantifier framework, and supports the view that the semantic value of proper names is of the same kind as that of other nouns – sets of individuals, whereas unique individuals are assigned as the value of the NP-level. Furthermore, it i s argued that the set denoted by a name contains the individuals name-related to the expression in question, i.e. the individuals bearing the name. In other uses (e.g. the museum bought a Picasso) the name denotes the extension of an ad hoc predicate. Finally, the relation between th e proposed analysis and Saussure's concept of the linguistic sign is briefly discussed.