Head-Driven Statistical Models for Natural Language Parsing

DOI10.1162/089120103322753356zbMath1234.68403WikidataQ56594413 ScholiaQ56594413MaRDI QIDQ3225404

Michael Collins

Publication date: 20 March 2012

Published in: Computational Linguistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/089120103322753356

zbMATH Keywords

ambiguity; statistical models; natural language parsing; lexicalized grammars; probabilistic context-free grammars

Mathematics Subject Classification ID

68Q42: Grammars and rewriting systems

68T50: Natural language processing

91F20: Linguistics

68Q87: Probability in computer science (algorithm analysis, random structures, phase transitions, etc.)

Related Items

Applications of Weighted Automata in Natural Language Processing, A Derivational Model of Discontinuous Parsing, Stochastic HPSG parse disambiguation using the redwoods corpus, A note on the expressive power of probabilistic context free grammars, Finite automata for compact representation of tuple dictionaries., A theory of learning from different domains, Bottom-up unranked tree-to-graph transducers for translation into semantic graphs, A derivational model of discontinuous parsing, Unsupervised and few-shot parsing from pretrained language models, Natural Language Processing, Moving from Rules to Data, Tree Transformations and Dependencies, The Generative Power of Probabilistic and Weighted Context-Free Grammars, Wide-Coverage Efficient Statistical Parsing with CCG and Log-Linear Models

Uses Software

• Penn Treebank

Cites Work

• Definite clause grammars for language analysis - A survey of the formalism and a comparison with augmented transition networks