Learning to parse natural language with maximum entropy models

DOI10.1023/A:1007502103375MaRDI QIDQ1289009zbMATH OpenOpenAlexFDO

Authors Adwait Ratnaparkhi

Publication date 24 May 1999

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1023/a:1007502103375

zbMATH Keywords

machine learning systemparsing natural language

Mathematics Subject Classification ID

Theory of compilers and interpreters (68N20) Natural language processing (68T50)

Recommendations

• Incorporating linguistic structure into maximum entropy language models
• Maximum entropy models for \(\Sigma_1\) sentences
• Probabilistic parsing using left corner language models
• Head-driven statistical models for natural language parsing
• Training parsers by inverse reinforcement learning
• Unsupervised and few-shot parsing from pretrained language models
• AI 2005: Advances in Artificial Intelligence

Cited in

(20)

• Optimal bandwidth selection for re-substitution entropy estimation
• scientific article; zbMATH DE number 1952675 (Why is no real title available?)
• Natural language processing (almost) from scratch
• Sample selection for statistical parsing
• AI 2005: Advances in Artificial Intelligence
• scientific article; zbMATH DE number 2033126 (Why is no real title available?)
• Training parsers by inverse reinforcement learning
• Learning tree patterns for syntactic parsing
• scientific article; zbMATH DE number 67828 (Why is no real title available?)
• Discriminative reranking for natural language parsing
• scientific article; zbMATH DE number 1875398 (Why is no real title available?)
• scientific article; zbMATH DE number 1931822 (Why is no real title available?)
• Head-driven statistical models for natural language parsing
• A locking-free meshfree method for the simulation of shear-deformable plates based on a mixed variational formulation
• Wide-coverage efficient statistical parsing with CCG and log-linear models
• \(P\)-top-\(k\) queries in a probabilistic framework from information extraction models
• Towards incremental parsing of natural language using recursive neural networks
• Towards effective parsing with neural networks: Inherent generalisations and bounded resource effects
• Consensus-based modeling using distributed feature construction with ILP
• Coarse-to-fine natural language processing

Describes a project that uses

Uses Software

• Penn Treebank

This page was built for publication: Learning to parse natural language with maximum entropy models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1289009)