Inducing History Representations for Broad Coverage Statistical Parsing

We present a neural network method for inducing representations of parse histories and using these history representations to estimate the probabilities needed by a statistical left-corner parser. The resulting statistical parser achieves performance (89.1% F-measure) on the Penn Treebank which is only 0.6% below the best current parser for this task, despite using a smaller vocabulary size and less prior linguistic knowledge. Crucial to this success is the use of structurally determined soft biases in inducing the representation of the parse history, and no use of hard independence assumptions.

• Publication year

  2003

• Venue

  North American Chapter of the Association for Computational Linguistics

• Publication date

  2003-05-27

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/1073445.1073459
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Generative versus Discriminative Models for Statistical Left-Corner Parsing

  2003influential reference
• Head-Driven Statistical Models for Natural Language Parsing

  2003influential reference
• New Ranking Algorithms for Parsing and Tagging: Kernels over Discrete Structures, and the Voted Perceptron

  2002cited by this paper
• What is the Minimal Set of Fragments that Achieves Maximal Parse Accuracy?

  2001cited by this paper
• Wide Coverage Incremental Parsing by Learning Attachment Preferences

  2001cited by this paper
• Incremental Syntactic Parsing of Natural Language Corpora with Simple Synchrony Networks

  2001cited by this paper
• A Neural Network Parser that Handles Sparse Data

  2000cited by this paper
• A Maximum-Entropy-Inspired Parser

  2000influential reference
• Discriminative Reranking for Natural Language Parsing

  2000influential reference
• Learning to Parse Natural Language with Maximum Entropy Models

  1999cited by this paper
• Efficient probabilistic top-down and left-corner parsing

  1999cited by this paper
• PCFG Models of Linguistic Tree Representations

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

  1997influential reference
• Probabilistic Parsing using Left Corner Language Models

  1997cited by this paper
• A Maximum Entropy Model for Part-Of-Speech Tagging

  1996cited by this paper
• Building a Large Annotated Corpus of English: The Penn Treebank

  1993influential reference
• Neural Networks for Pattern Recognition

  1993influential reference
• Multilayer feedforward networks are universal approximators

  1989cited by this paper

• Transformers as Graph-to-Graph Models

  2023cites this paper
• Hermes: Unlocking Security Analysis of Cellular Network Protocols by Synthesizing Finite State Machines from Natural Language Specifications

  2023cites this paper
• Context-Free Grammars and Constituency Parsing

  2023cites this paper
• Fast Rule-Based Decoding: Revisiting Syntactic Rules in Neural Constituency Parsing

  2022cites this paper
• Towards syntax-aware token embeddings

  2020cites this paper
• The Unstoppable Rise of Computational Linguistics in Deep Learning

  2020influential citation
• Abundance and Phenotypic Diversity of the Medicinal Sideritis Scardica Griseb. in Relation to Floristic Composition of Its Habitat in Northern Greece

  2020cites this paper
• Tetra-Tagging: Word-Synchronous Parsing with Linear-Time Inference

  2019cites this paper
• Multitask Pointer Network for Korean Dependency Parsing

  2019cites this paper
• Bayesian Analysis in Natural Language Processing, Second Edition

  2019cites this paper
• Graph-to-Graph Transformer for Transition-based Dependency Parsing

  2019cites this paper
• LSTMs Can Learn Syntax-Sensitive Dependencies Well, But Modeling Structure Makes Them Better

  2018cites this paper
• Improving Feature-Rich Transition-Based Constituent Parsing Using Recurrent Neural Networks

  2017cites this paper
• Greedy Transition-Based Dependency Parsing with Stack LSTMs

  2017cites this paper
• Bag-of-Vector Embeddings of Dependency Graphs for Semantic Induction

  2017cites this paper
• CLCL (Geneva) DINN Parser: a Neural Network Dependency Parser Ten Years Later

  2017cites this paper
• Arc-Standard Spinal Parsing with Stack-LSTMs

  2017cites this paper
• Improving Neural Parsing by Disentangling Model Combination and Reranking Effects

  2017cites this paper
• Left-Corner Parsing for Identifying PTB-Style Nonlocal Dependencies

  2017cites this paper
• Effective Inference for Generative Neural Parsing

  2017cites this paper
• Fast(er) Exact Decoding and Global Training for Transition-Based Dependency Parsing via a Minimal Feature Set

  2017cites this paper
• CYK Parsing over Distributed Representations

  2017cites this paper
• A Generative Parser with a Discriminative Recognition Algorithm

  2017cites this paper
• Incremental generative models for syntactic and semantic natural language processing

  2017cites this paper
• Structured learning with inexact search: advances in shift-reduce CCG parsing

  2017cites this paper
• Neural Network Based Named Entity Recognition

  2017cites this paper
• Transition-Based Left-Corner Parsing for Identifying PTB-Style Nonlocal Dependencies

  2016cites this paper
• Prédiction structurée pour l’analyse syntaxique en constituants par transitions : modèles denses et modèles creux [Structured Prediction for Transition-based Constituent Parsing: Dense and Sparse Models]

  2016cites this paper
• Towards a Universal Analyzer of Natural Languages

  2016cites this paper
• Recurrent Neural Network Grammars

  2016cites this paper
• Indonesian shift-reduce constituent parser

  2016cites this paper
• Incremental Parsing with Minimal Features Using Bi-Directional LSTM

  2016cites this paper
• Many Languages, One Parser

  2016cites this paper
• Globally Normalized Transition-Based Neural Networks

  2016cites this paper
• Algorithms for Identifying Syntactic Errors and Parsing with Graph Structured Output

  2016cites this paper
• JOINT RNN-BASED GREEDY PARSING AND WORD

  2015cites this paper
• Refinements in Syntactic Parsing

  2015cites this paper
• Generative models for syntactic and semantic structure prediction using latent variables

  2015cites this paper
• Neural CRF Parsing

  2015cites this paper
• Transition-based Neural Constituent Parsing

  2015influential citation
• Incremental Recurrent Neural Network Dependency Parser with Search-based Discriminative Training

  2015cites this paper
• Joint RNN-Based Greedy Parsing and Word Composition

  2014cites this paper
• Grammar as a Foreign Language

  2014cites this paper
• Less Grammar, More Features

  2014cites this paper
• Multilingual Joint Parsing of Syntactic and Semantic Dependencies with a Latent Variable Model

  2013influential citation
• Learning to Disambiguate Syntactic Relations

  2013cites this paper
• Multilingual Joint Parsing of Syntactic and Semantic Dependencies with a Latent Variable Model

  2013cites this paper
• Parser Showdown at the Wall Street Corral: An Empirical Investigation of Error Types in Parser Output

  2012cites this paper
• The Geometry of Constrained Structured Prediction: Applications to Inference and Learning of Natural Language Syntax

  2012cites this paper
• Data-Driven Methods for Spoken Language Understanding

  2012cites this paper
• Human resource management in domestic vs. multinational enterprises: an investigation in the country of Brunei

  2012cites this paper
• for Modelling Unbounded Structures

  2011cites this paper
• Bayesian Network Automata for Modelling Unbounded Structures

  2011cites this paper
• D2.5: Improved models of syntactic-semantic parsing, for English and French

  2011cites this paper
• Incremental Sigmoid Belief Networks for Grammar Learning

  2010cites this paper
• Class-based approach to disambiguating Levin verbs

  2010cites this paper
• Supertagging: Using Complex Lexical Descriptions in Natural Language Processing

  2010cites this paper
• Current Trends in Parsing Technology

  2010cites this paper
• Top-Down Nearly-Context-Sensitive Parsing

  2010cites this paper
• D 2 . 2 : Semantic Decoder which Exploits Syntactic-Semantic Parsing , for the TownInfo Task

  2009cites this paper
• Year : 2003 Learning to Disambiguate Syntactic Relations

  2009cites this paper
• Discriminative Training of the Hidden Vector State Model for Semantic Parsing

  2009cites this paper
• Domain Adaptation with Artificial Data for Semantic Parsing of Speech

  2009cites this paper
• Deriving lexical and syntactic expectation-based measures for psycholinguistic modeling via incremental top-down parsing

  2009cites this paper
• Unlexicalised Hidden Variable Models of Split Dependency Grammars

  2008cites this paper
• Hybrid Methods for Acquisition of Lexical Information: the Case for Verbs

  2008influential citation
• Towards a machine-learning architecture for lexical functional grammar parsing

  2008cites this paper
• Semantic Parsing for High-Precision Semantic Role Labelling

  2008cites this paper
• Global Inference and Learning Algorithms for Multi-Lingual Dependency Parsing

  2008cites this paper
• Exploiting non-linear probabilistic models in natural language parsing and reranking

  2008influential citation
• Incremental Bayesian networks for structure prediction

  2007influential citation
• Fast and Robust Multilingual Dependency Parsing with a Generative Latent Variable Model

  2007cites this paper
• Constituent Parsing with Incremental Sigmoid Belief Networks

  2007influential citation
• Pro3Gres Parser in the CoNLL Domain Adaptation Shared Task

  2007cites this paper
• Better training for function labeling

  2007cites this paper
• A Latent Variable Model for Generative Dependency Parsing

  2007influential citation
• Robust Parsing of the Proposition Bank

  2006influential citation
• Accurate Parsing of the Proposition Bank

  2006cites this paper
• Fully Parsing the Penn Treebank

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

  2006cites this paper
• Learning Phrasal Categories

  2006cites this paper
• Loss Minimization in Parse Reranking

  2006cites this paper
• Porting Statistical Parsers with Data-Defined Kernels

  2006influential citation
• Bayes Risk Minimization in Natural Language Parsing

  2006cites this paper
• Constituent Parsing by Classification

  2005influential citation
• Deriving kernels from MLP probability estimators for large categorization problems

  2005cites this paper
• Assigning Function Labels to Unparsed Text

  2005cites this paper
• Data-Defined Kernels for Parse Reranking Derived from Probabilistic Models

  2005influential citation
• Probabilistic CFG with Latent Annotations

  2005cites this paper
• Dependency Grammar and Dependency Parsing

  2005cites this paper
• A Neural Syntactic Language Model

  2005cites this paper
• Kernels from Probabilistic Models for Multiclass Classification and Reranking with Arbitrary Loss Function

  2005influential citation
• DerivingKernelsfrom MLP Probability Estimators forLargeCategorization Problems

  2005cites this paper
• Lexical and Structural Biases for Function Parsing

  2005influential citation
• Accurate Function Parsing

  2005influential citation
• for Large Categorization Problems

  2005cites this paper
• ESSLLI 2004 Workshop on Combining Shallow and Deep Processing for NLP

  2004cites this paper
• Combining shallow and deep processing for a robust, fast, deep-linguistic dependency parser

  2004cites this paper
• Style Recognition Using Shallow Statistical Analysis 1

  2004cites this paper
• Fast, Deep-Linguistic Statistical Dependency Parsing

  2004cites this paper