A parallel approach to syntax for generation

Abstract

To produce good utterances from non-trivial inputs a natural language generator should consider many words in parallel, which raises the question of how to handle syntax in a parallel generator. If a generator is incremental and centered on the task of word choice, then the role of syntax is merely to help evaluate the appropriateness of words. One way to do this is to represent syntactic knowledge as an inventory of "syntactic constructions" and to have many constructions active in parallel at run-time. If this is done then the syntactic form of utterances can be emergent, resulting from synergy among constructions, and there is no need to build up or manipulate representations of syntactic structure. This approach is implemented in FIG, an incremental generator based on spreading activation, in which syntactic knowledge is represented in the same network as world knowledge and lexical knowledge.

Language Control and Code-switching

“…However, the net result is that selection reflects items and constructions that are the most appropriate at that moment in time from the speaker's perspective on the basis of pragmatic, semantic, syntactic and collocational considerations and readiness for use (cf. Ward 1992).…”

Gaze durations during speech reflect word selection and phonological encoding

“…If so, they should take longer to begin the description when B is lower is codability, but the codability of C should matter only after they begin speaking. Or third, they could select the names as needed (De Smedt & Ward, 1992). If they do, they should take no longer to begin speaking when either B or C is lower in codability.…”