Three Generative, Lexicalised Models for Statistical Parsing

Abstract

In this paper we first propose a new statistical parsing model, which is a generative model of lexicalised context-free grammar. We then extend the model to include a probabilistic treatment of both subcategorisation and wh-movement. Results on Wall Street Journal text show that the parser performs at 88.1/87.5% constituent precision/recall, an average improvement of 2.3% over (Collins 96).

8 pages, to appear in Proceedings of ACL/EACL 97.

References in corpus (1)

• Statistical Decision-Tree Models for Parsing

Cited by in corpus (20)

• Grammar as a Foreign Language
• Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
• Cross-lingual Annotation Projection for Semantic Roles
• A Tutorial on Dual Decomposition and Lagrangian Relaxation for Inference in Natural Language Processing
• Acquiring Word-Meaning Mappings for Natural Language Interfaces
• Faster Shift-Reduce Constituent Parsing with a Non-Binary, Bottom-Up Strategy
• Using Syntax-Based Machine Translation to Parse English into Abstract Meaning Representation
• Parsing with Traces: An $O(n^4)$ Algorithm and a Structural Representation
• What Do Recurrent Neural Network Grammars Learn About Syntax?
• A Bayesian Model for Generative Transition-based Dependency Parsing
• What is the minimal set of fragments that achieves maximal parse accuracy?
• Mimic and Conquer: Heterogeneous Tree Structure Distillation for Syntactic NLP
• Left-corner Methods for Syntactic Modeling with Universal Structural Constraints
• Semantic Parsing of Mathematics by Context-based Learning from Aligned Corpora and Theorem Proving
• The effect of alternative tree representations on tree bank grammars
• Arc-Standard Spinal Parsing with Stack-LSTMs
• A natural language interface to a graph-based bibliographic information retrieval system
• Lexicalized Stochastic Modeling of Constraint-Based Grammars using Log-Linear Measures and EM Training
• The Structured Weighted Violations Perceptron Algorithm
• A Context-theoretic Framework for Compositionality in Distributional Semantics