Assigning Grammatical Relations with a Back-off Model

1997/06/04 by Erika F. de Lima, de Lima, Erika F.
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #cmp-lg #cs.CL

paper · pdf · doi:10.48550/arxiv.cmp-lg/9706001

To appear in Proceedings of the Second Conference on Empirical Methods in Natural Language Processing, 7 pages, LaTeX

arxiv created 1997/06/04 · arxiv updated 2009/11/30

Abstract

This paper presents a corpus-based method to assign grammatical subject/object relations to ambiguous German constructs. It makes use of an unsupervised learning procedure to collect training and test data, and the back-off model to make assignment decisions.

Related

• Syntactic Analyses for Parallel Grammars: Auxiliaries and Genitive NPs
• Automatic Inference of DATR Theories
• Grammatical cues to subjecthood are redundant in a majority of simple clauses across languages
• Where Defaults Don't Help: the Case of the German Plural System
• (Generalized Linear) Mixed‐Effects Modeling: A Learner Corpus Example