Sixth European Conference on Speech Communication and Technology

Budapest, Hungary
September 5-9, 1999

Efficient Sentence Disambiguation by Preferred Constituent Order

S. Kronenberg (1), K. Skuplik (2)

University of Bielefeld, (1) Technische Fakultät, (2) Fakultät für Linguistik und Literaturwissenschaft, Bielefeld, Germany

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.