Exploiting Diversity in Natural Language Processing: Combining Parsers

Three state-of-the-art statistical parsers are combined to produce more accurate parses, as well as new bounds on achievable Treebank parsing accuracy. Two general approaches are presented and two combination techniques are described for each approach. Both parametric and non-parametric models are explored. The resulting parsers surpass the best previously published performance results for the Penn Treebank.

• Publication year

  2000

• Venue

  Conference on Empirical Methods in Natural Language Processing

• Publication date

  2000-06-01

• Fields of study

  Linguistics, Computer Science

• Identifiers
  arXiv cs/0006003
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Improving Data Driven Wordclass Tagging by System Combination

  1998cited by this paper
• Improving Data Driven Wordclass Tagging by System Combination

  1998cited by this paper
• Exploiting Diverse Knowledge Sources via Maximum Entropy in Named Entity Recognition

  1998cited by this paper
• Statistical Parsing with a Context-Free Grammar and Word Statistics

  1997cited by this paper
• Three Generative, Lexicalised Models for Statistical Parsing

  1997cited by this paper
• A Linear Observed Time Statistical Parser Based on Maximum Entropy Models

  1997cited by this paper
• A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER)

  1997cited by this paper
• Three Heads are Better than One

  1994cited by this paper
• Building a Large Annotated Corpus of English: The Penn Treebank

  1993cited by this paper
• Stacked generalization

  1992cited by this paper

• Improving Semantic Parsing for Task Oriented Dialog

  2019cites this paper
• Naïve Bayes for Function Tagging in Myanmar Language

  2018cites this paper
• Explainable Improved Ensembling for Natural Language and Vision

  2018cites this paper
• Task-based parser output combination : workflow and infrastructure

  2018influential citation
• Neural Parse Combination

  2017cites this paper
• Toward Solving Penn Treebank Parsing

  2017influential citation
• A Derivational Model of Discontinuous Parsing

  2017cites this paper
• Stacking With Auxiliary Features: Improved Ensembling for Natural Language and Vision

  2016cites this paper
• Combining Supervised and Unsupervised Enembles for Knowledge Base Population

  2016cites this paper
• A Survey of Lexical Functional Grammar in the Arabic Contex

  2016cites this paper
• Supervised and Unsupervised Ensembling for Knowledge Base Population

  2016cites this paper
• Parsing modern standard Arabic using Treebank resources

  2015cites this paper
• Syntactic Parse Fusion

  2015cites this paper
• Diversity in Spectral Learning for Natural Language Parsing

  2015cites this paper
• Iterative parameter mixing for distributed large-margin training of structured predictors for natural language processing

  2015cites this paper
• Bilexical Dependencies as an Intermedium for Data-Driven and HPSG-Based Parsing

  2015cites this paper
• System Combination for Multi-document Summarization

  2015cites this paper
• Knowledge base population using stacked ensembles of information extractors

  2015cites this paper
• Stacked Ensembles of Information Extractors for Knowledge-Base Population

  2015cites this paper
• Intelligent Combination of Structural Analysis Algorithms: Application to Mathematical Expression Recognition

  2014cites this paper
• Combining strategies for tagging and parsing Arabic

  2014cites this paper
• Exploiting limited data for parsing

  2014cites this paper
• A study on cost behaviors of binary classification measures in class-imbalanced problems

  2014cites this paper
• Data-driven, PCFG-based and Pseudo-PCFG-based Models for Chinese Dependency Parsing

  2013cites this paper
• New Template-Template-enhanced ICALL System for a Second Language Composition Course

  2013cites this paper
• 4-4 Direct Use of Syntactic Information for Machine Translation System Combination

  2013cites this paper
• Combining PCFG-LA Models with Dual Decomposition: A Case Study with Function Labels and Binarization

  2013cites this paper
• System Combination with Extra Alignment Information

  2012cites this paper
• Parsing of Myanmar sentences with function tagging

  2012cites this paper
• Approximating Theoretical Linguistics Classification in Real Data: the Case of German “nach” Particle Verbs

  2012cites this paper
• Learning Chinese language structures with multiple views

  2012cites this paper
• Detecting grammatical errors with treebank-induced, probabilistic parsers

  2012cites this paper
• Evaluación de sistemas de búsqueda y validación de respuestas

  2012cites this paper
• Combining Multiple Alignments to Improve Machine Translation

  2012cites this paper
• Ensembles of diverse clustering-based discriminative dependency parsers

  2012cites this paper
• Machine transliteration survey

  2011cites this paper
• Analyzing and Integrating Dependency Parsers

  2011cites this paper
• From News to Comment: Resources and Benchmarks for Parsing the Language of Web 2.0

  2011cites this paper
• Combining Polish Morphosyntactic Taggers

  2011cites this paper
• Statistical Function Tagging and Grammatical Relations of Myanmar Sentences

  2011cites this paper
• Machine Translation System Combination by Confusion Forest

  2011cites this paper
• Syntactic Analysis of Myanmar Language

  2011cites this paper
• Research on Rule-based Chinese Syntactic Parsing Postprocess Using Verb Subcategorization

  2011cites this paper
• Improved Parsing for Arabic by Combining Diverse Dependency Parsers

  2011cites this paper
• Research on Verb Subcategorization-Based Syntactic Parsing Postprocess for Chinese Language

  2010influential citation
• Context Adaptation in Statistical Machine Translation Using Models with Exponentially Decaying Cache Domain Adaptation to Summarize Human Conversations Exploring Representation-learning Approaches to Domain Adaptation Using Domain Similarity for Performance Estimation Self-training without Reranking

  2010cites this paper
• Ensemble Models for Dependency Parsing: Cheap and Good?

  2010cites this paper
• Products of Random Latent Variable Grammars

  2010cites this paper
• Parsing as Classification

  2010cites this paper
• Formalizing the Use and Characteristics of Constraints in Pipeline Systems

  2010cites this paper
• La Combinación de Sistemas y el PLN

  2010cites this paper
• Self-Training without Reranking for Parser Domain Adaptation and Its Impact on Semantic Role Labeling

  2010cites this paper
• Integrating Parsing and Word Alignment in Syntax-Based Machine Translation

  2010influential citation
• Transformation and Combination in Data-Driven Dependency Parcing

  2009cites this paper
• A special parser for learning English composition - Error analysis & learners' model for ILTS

  2009cites this paper
• K-Best Combination of Syntactic Parsers

  2009influential citation
• Co-Parsing with Competitive Models

  2009cites this paper
• Co-Parsing with Competitive Models

  2009cites this paper
• Joint Decoding with Multiple Translation Models

  2009cites this paper
• Charles University in Prague Faculty of Mathematics and Physics Master's Thesis

  2009cites this paper
• Combining Constituent Parsers

  2009cites this paper
• Better Parser Combination

  2009cites this paper
• Clustering Words by Syntactic Similarity improves Dependency Parsing of Predicate-argument Structures

  2009cites this paper
• Improving the accuracy of Natural Language Dependency Parsing

  2008cites this paper
• Machine Transliteration of Proper Names between

  2008cites this paper
• Dependency Parsing by Transformation and Combination

  2008cites this paper
• Large scale production of syntactic annotations for French

  2008cites this paper
• Experimentos con un sistema combinado de analizadores sintacticos de dependencias para el espa~ nol

  2008cites this paper
• Machine transliteration of proper names between English and Persian

  2008cites this paper
• Evaluation and interoperable annotations: the point of view of a parser developer

  2008cites this paper
• Experiments with an ensemble of Spanish dependency parsers

  2008cites this paper
• From knowledge acquisition to information retrieval

  2008cites this paper
• Semantic Role Labeling Tools Trained on the Cast3LB-CoNNL-SemRol Corpus

  2008cites this paper
• Experiments with an ensemble of Spanish dependency parsers

  2008cites this paper
• Acknowledgement 3 Invited Speakers 5

  2007cites this paper
• Dissolving the 'd/dt' disambiguation problem

  2007cites this paper
• Learning for semantic parsing with kernels under various forms of supervision

  2007cites this paper
• Hybrid Parsing with a Maximum Spanning Tree Predictor

  2007cites this paper
• Improved Processing of Textual Use Cases: Deriving Behavior Specifications

  2007cites this paper
• Improving the Performance of a Tagger Generator in an Information Extraction Application

  2007cites this paper
• Combining Similarity-based Approaches for Semantic Tagging of Unknown Words

  2007cites this paper
• Charting Democracy Across Parsers

  2007influential citation
• ii Preface

  2007cites this paper
• FRAMEWORK AND RESOURCES FOR NATURAL LANGUAGE

  2007cites this paper
• Framework and Resources for Natural Language Parser Evaluation

  2007cites this paper
• Ampliación automática de corpus mediante la colaboración de varios etiquetadores

  2006cites this paper
• A Comparison of Dependency Parsers for German Master ’ s Thesis in Computational Linguistics

  2006cites this paper
• TextRank como motor de aprendizaje en tareas de etiquetado

  2006cites this paper
• A Fast, Accurate Deterministic Parser for Chinese

  2006cites this paper
• Minority Vote: At-Least-N Voting Improves Recall for Extracting Relations

  2006cites this paper
• Parser Combination by Reparsing

  2006cites this paper
• Support Vector Machines to Weight Voters in a Voting System of Entity Extractors

  2006cites this paper
• Discriminative learning and spanning tree algorithms for dependency parsing

  2006cites this paper
• Automatically Inducing a Part-of-Speech Tagger by Projecting from Multiple Source Languages Across Aligned Corpora

  2005cites this paper
• Improving dependency analysis by syntactic parser combination

  2005influential citation
• Evaluating and Integrating Treebank Parsers on a Biomedical Corpus

  2005cites this paper
• Parsing of Grammatical Relations in Transcripts of Parent-Child Dialogs

  2005cites this paper
• Applying Stacking and Corpus Transformation to a Chunking Task

  2005cites this paper
• The automatic acquisition of knowledge about discourse connectives

  2005cites this paper
• A Kernel-based Approach to Learning Semantic Parsers

  2005cites this paper