Sixth European Conference on Speech Communication and Technology
A major problem with (partially) free constituent order is to manifest preferences among structurally distinct parses of ambiguous sentences. In order to obtain scoring criteria a preferred constituent order can considerably support a best-first strategy. This work presents an experimentally evaluated model of preferred German constituent order in the middle field and its application for the implementation of a robust and eficient parsing strategy for spontaneous speech. This constituent order is used to guide the parallel LR(1)-parser to derive the preferred interpretation of ambiguous sentences.
Full Paper (PDF) Gnu-Zipped Postscript
Bibliographic reference. Kronenberg, S. / Skuplik, K. (1999): "Efficient sentence disambiguation by preferred constituent order", In EUROSPEECH'99, 1999-2002.