Assigning Grammatical Relations with a Back-off Model

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.

• Publication year

  1997

• Venue

  Conference on Empirical Methods in Natural Language Processing

• Publication date

  1997-06-04

• Fields of study

  Linguistics, Computer Science

• Identifiers
  arXiv cmp-lg/9706001
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Prepositional Phrase Attachment through a Backed-off Model

  1995cited by this paper
• A Maximum Entropy Model for Prepositional Phrase Attachment

  1994cited by this paper
• Structural Ambiguity and Lexical Relations

  1991cited by this paper
• Estimation of probabilities from sparse data for the language model component of a speech recognizer

  1987influential reference

• Statistical models for case ambiguity resolution in Korean

  2005cites this paper
• YAP: parsing and disambiguation with feature based grammars

  1999cites this paper
• Tagging and parsing with cascaded Markov models: automation of corpus annotation

  1999cites this paper
• Genetic optimization of neural network configurations for natural language learning

  1999cites this paper
• Maximum entropy models for natural language ambiguity resolution

  1998cites this paper