What is the Minimal Set of Fragments that Achieves Maximal Parse Accuracy?

We aim at finding the minimal set of fragments which achieves maximal parse accuracy in Data Oriented Parsing. Experiments with the Penn Wall Street Journal treebank show that counts of almost arbitrary fragments within parse trees are important, leading to improved parse accuracy over previous models tested on this treebank (a precision of 90.8% and a recall of 90.6%). We isolate some dependency relations which previous models neglect but which contribute to higher parse accuracy.

• Publication year

  2001

• Venue

  Annual Meeting of the Association for Computational Linguistics

• Publication date

  2001-07-06

• Fields of study

  Physics, Computer Science

• Identifiers
  DOI 10.3115/1073012.1073022arXiv cs/0110050
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Head-Driven Statistical Models for Natural Language Parsing

  2003influential reference
• Data-Oriented Parsing

  2003influential reference
• Using natural language processing techniques for musical parsing

  2001cited by this paper
• A Maximum-Entropy-Inspired Parser

  2000influential reference
• Parsing with the Shortest Derivation

  2000influential reference
• An Improved Parser for Data-Oriented Lexical-Functional Analysis

  2000cited by this paper
• Statistical Parsing with an Automatically-Extracted Tree Adjoining Grammar

  2000influential reference
• Tree-gram Parsing: Lexical Dependencies and Structural Relations

  2000cited by this paper
• Discriminative Reranking for Natural Language Parsing

  2000influential reference
• Combining semantic and syntactic structure for language modeling

  2000cited by this paper
• A New Probability Model for Data Oriented Parsing

  1999cited by this paper
• Learning Efficient Disambiguation

  1999influential reference
• A Probabilistic Corpus-Driven Model for Lexical-Functional Analysis

  1998cited by this paper
• Improved Boosting Algorithms Using Confidence-rated Predictions

  1998influential reference
• Book Reviews: Beyond Grammar: An Experience-based Theory of Language

  1998influential reference
• PCFG Models of Linguistic Tree Representations

  1998influential reference
• Parsing Inside-Out

  1998influential reference
• Global Thresholding and Multiple-Pass Parsing

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

  1997influential reference
• Bilexical Grammars and a Cubic-time Probabilistic Parser

  1997cited by this paper
• Statistical Parsing with a Context-Free Grammar and Word Statistics

  1997influential reference
• Encoding Frequency Information in Lexicalized Grammars

  1997cited by this paper
• Efficient Algorithms for Parsing the DOP Model

  1996cited by this paper
• Three New Probabilistic Models for Dependency Parsing: An Exploration

  1996cited by this paper
• Tree-Bank Grammars

  1996influential reference
• A New Statistical Parser Based on Bigram Lexical Dependencies

  1996cited by this paper
• Two Questions about Data-Oriented Parsing

  1996cited by this paper
• Stochastic Lexicalized Tree-Insertion Grammar

  1996influential reference
• Statistical Decision-Tree Models for Parsing

  1995cited by this paper
• Using an Annotated Language Corpus as a Virtual Stochastic Grammar

  1993cited by this paper
• Coping with Ambiguity and Unknown Words through Probabilistic Models

  1993cited by this paper
• Building a Large Annotated Corpus of English: The Penn Treebank

  1993cited by this paper
• Stochastic Lexicalized Tree-adjoining Grammars

  1992cited by this paper

• Combining Simplicity and Likelihood in Language and Music

  2019influential citation
• Preprocessing Does Matter: Parsing Non-Segmented Arabic

  2018cites this paper
• Data-Oriented Parsing with Discontinuous Constituents and Function Tags

  2016cites this paper
• Aligning the foundations of hierarchical statistical machine translation

  2016cites this paper
• Multiword Expression Identification with Recurring Tree Fragments and Association Measures

  2015cites this paper
• Automatically generating reading lists

  2014cites this paper
• Identifying Multi-Word Expressions in Large Treebanks with Tree Kernels

  2014cites this paper
• Getting Rid Of Numbers DOP without Probability Theory ?

  2013cites this paper
• Discontinuous Parsing with an Efficient and Accurate DOP Model

  2013cites this paper
• Bayesian Tree Substitution Grammars as a Usage-based Approach

  2013influential citation
• Data-oriented Parsing

  2013cites this paper
• Structured cognition and neural systems: from rats to language.

  2012cites this paper
• Self-Training Tree Substitution Grammars for Domain Adaptation

  2012cites this paper
• A New DOP Model for Phrase-structure Parsing of Persian Sentences

  2012cites this paper
• An All-Fragments Grammar for Simple and Accurate Parsing

  2012cites this paper
• Decomposing and regenerating syntactic trees

  2012cites this paper
• Toward Tree Substitution Grammars with Latent Annotations

  2012cites this paper
• Judging Grammaticality with Tree Substitution Grammar Derivations

  2011cites this paper
• The Surprising Variance in Shortest-Derivation Parsing

  2011cites this paper
• Accurate Parsing with Compact Tree-Substitution Grammars: Double-DOP

  2011cites this paper
• Discontinuous Data-Oriented Parsing through Mild Context-Sensitivity

  2011cites this paper
• Simple, Accurate Parsing with an All-Fragments Grammar

  2010cites this paper
• UvA-DARE ( Digital Academic Repository ) Efficiently extract recurring tree fragments from large treebanks

  2010cites this paper
• Statistical parsing of noun phrase structure

  2010cites this paper
• Factors Affecting the Accuracy of Korean Parsing

  2010cites this paper
• Bayesian Learning of a Tree Substitution Grammar

  2009influential citation
• Language Modeling with Tree Substitution Grammars

  2009cites this paper
• A simple DOP model for constituency parsing of Italian sentences

  2009cites this paper
• Weight Pushing and Binarization for Fixed-Grammar Parsing

  2009influential citation
• A Dependency Parsing Approach to Biomedical Text Mining

  2008cites this paper
• Simulating & Reranking Data-oriented Parsing

  2008cites this paper
• Reducing Bias Effects in DOP Parameter Estimation

  2008cites this paper
• Statistical parsing with an automatically extracted tree adjoining grammar

  2007cites this paper
• Grammatical feature data-oriented parsing

  2007cites this paper
• Parsimonious Data-Oriented Parsing

  2007cites this paper
• Attempto Controlled English Meets the Challenges of Knowledge Representation, Reasoning, Interoperability and User Interfaces

  2006cites this paper
• Realizing Target Language Generation in Data-Oriented English-Chinese Machine Translation

  2006cites this paper
• A Consistent and Efficient Estimator for Data-Oriented Parsing

  2005cites this paper
• Collaborative and corpus-driven approaches towards lexicalized grammar-based natural language processing

  2005cites this paper
• Boosting-based Parse Reranking with Subtree Features

  2005influential citation
• Data-oriented models of parsing and translation

  2005cites this paper
• Knowledge source construction in data-oriented English-Chinese machine translation

  2005cites this paper
• Wide coverage natural language processing using kernel methods and neural networks for structured data

  2005cites this paper
• Research on DOP-based Chinese parsing

  2005influential citation
• A L A T E X Package for CSLI Collections

  2004cites this paper
• Semi-Automatic Construction of a Question Treebank

  2004cites this paper
• Paraphrasing as Machine Translation (自然言語処理特集号「言い換え」)

  2004cites this paper
• Inducing History Representations for Broad Coverage Statistical Parsing

  2003cites this paper
• Structured Parameter Estimation for LFG-DOP using Backoff

  2003influential citation
• A DOP model for lexical-functional grammar

  2003cites this paper
• An efficient implementation of a new DOP model

  2003influential citation
• An island-driven parsing system

  2003cites this paper
• Data and models for statistical parsing with combinatory categorial grammar

  2003cites this paper
• Comparing Convolution Kernels and Recursive Neural Networks for Learning Preferences on Structured Data

  2003cites this paper
• Backoff Parameter Estimation for the DOP Model

  2003cites this paper
• Incremental nonmonotonic parsing through semantic self-organization

  2003cites this paper
• Head-Driven Statistical Models for Natural Language Parsing

  2003cites this paper
• Structured parameter estimation for LFG-DOP

  2003influential citation
• A dop model for phrase structure trees

  2003cites this paper
• Seeing the wood for the trees: data-oriented translation

  2003cites this paper
• Backoff DOP: Parameter Estimation by Backoff

  2003influential citation
• Extracting stochastic grammars from treebanks

  2003cites this paper
• Antecedent Recovery: Experiments with a Trace Tagger

  2003cites this paper
• Neural Network Probability Estimation for Broad Coverage Parsing

  2003cites this paper
• Back-off as Parameter Estimation for DOP models

  2002cites this paper
• Fast Exact Inference with a Factored Model for Natural Language Parsing

  2002cites this paper
• A Data-Oriented Parsing Model for Lexical-Functional Grammar

  2002influential citation
• Memory-Based Shallow Parsing

  2002cites this paper
• A General Parsing Model for Music and Language

  2002cites this paper
• New Ranking Algorithms for Parsing and Tagging: Kernels over Discrete Structures, and the Voted Perceptron

  2002influential citation
• Memory-Based Grammatical Relation Finding

  2002cites this paper
• Combining labeled and unlabeled data in statistical natural language parsing

  2002cites this paper
• Rescoring effectiveness of language models using different levels of knowledge and their integration

  2002cites this paper
• A Graph Topological Representation of Melody Scores

  2002cites this paper
• Fast Exact Inference with a Factored Model for Natural Language Parsing

  2002cites this paper
• The SuperARV Language Model: Investigating the Effectiveness of Tightly Integrating Multiple Knowledge Sources

  2002cites this paper
• A Unified Model of Structural Organization in Language and Music

  2002influential citation
• Using natural language processing techniques for musical parsing

  2001cites this paper
• 1 Efficient parsing of DOP with PCFG-reductions – DRAFT

  2001influential citation
• Immediate-Head Parsing for Language Models

  2001cites this paper
• Probabilistic grammars for music

  2001cites this paper
• Statistical Parsing with an Automatically-Extracted Tree Adjoining Grammar

  2000cites this paper
• Beyond PARSEVAL — Towards Improved Evaluation Measures for Parsing Systems

  year unknowncites this paper
• Towards Simpler Tree Substitution Grammars Msc in Logic

  year unknowncites this paper
• Chapter 1 Statistical Parsing 1.1 Introduction

  year unknowncites this paper
• Extending the Tree-DOP Model with Grammatical Function Information 1 Background and motivation : issues for LFG-DOP Data-Oriented Parsing

  year unknowncites this paper
• Mapping Low-level Linguistic Representations onto Interpretations for Cognitive Systems using Data Driven Methods

  year unknowncites this paper
• A Consistent and Efficient Estimator for the Data-oriented Parsing Model

  year unknowncites this paper