Effective Self-Training for Parsing

We present a simple, but surprisingly effective, method of self-training a two-phase parser-reranker system using readily available unlabeled data. We show that this type of bootstrapping is possible for parsing when the bootstrapped parses are processed by a discriminative reranker. Our improved model achieves an f-score of 92.1%, an absolute 1.1% improvement (12% error reduction) over the previous best result for Wall Street Journal parsing. Finally, we provide some analysis to better understand the phenomenon.

• Publication year

  2006

• Venue

  North American Chapter of the Association for Computational Linguistics

• Publication date

  2006-06-04

• Fields of study

  Computer Science

• Identifiers
  DOI 10.3115/1220835.1220855
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• MAP adaptation of stochastic grammars

  2006cited by this paper
• Better k-best Parsing

  2005cited by this paper
• Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking

  2005influential reference
• Discriminative Training of a Neural Network Statistical Parser

  2004cited by this paper
• Bootstrapping statistical parsers from small datasets

  2003influential reference
• Bootstrapping POS-taggers using unlabelled data

  2003cited by this paper
• A Generative Constituent-Context Model for Improved Grammar Induction

  2002cited by this paper
• Corpus Variation and Parser Performance

  2001cited by this paper
• PAC Generalization Bounds for Co-training

  2001cited by this paper
• Applying Co-Training Methods to Statistical Parsing

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

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

  2000cited by this paper
• Computation of the N Best Parse Trees for Weighted and Stochastic Context-Free Grammars

  2000cited by this paper
• Estimators for Stochastic “Unification-Based” Grammars

  1999cited by this paper
• Statistical Parsing with a Context-Free Grammar and Word Statistics

  1997cited by this paper
• An Empirical Study of Smoothing Techniques for Language Modeling

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

  1993cited by this paper
• Structural Ambiguity and Lexical Relations

  1991cited by this paper
• of the Association for Computational Linguistics

  year unknowncited by this paper

• PLLM: Pseudo-Labeling Large Language Models for CAD Program Synthesis

  2026cites this paper
• Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models

  2026cites this paper
• Semi-supervised learning for dose prediction in targeted radionuclide therapy: a synthetic data study

  2026cites this paper
• Dual-view cross attention enhanced semi-supervised learning method for discourse cognitive engagement classification in online course discussions

  2025cites this paper
• An open-set few-shot face recognition framework with balanced adaptive cohesive mixing

  2025cites this paper
• Manod: A multi-modal anomaly detection framework for distributed system

  2025cites this paper
• Semi-supervised federated learning for collaborative security threat detection in control system for distributed power generation

  2025cites this paper
• Revisiting semi-supervised learning in the era of foundation models

  2025cites this paper
• A pseudo-labeling approach based on knowledge distillation for graph few-shot learning

  2025cites this paper
• A Dual-Channel Iterative Method Integrating Semi-supervised Self-Training and Interpretable Deep Learning Models for Mineral Prospectivity Prediction

  2025cites this paper
• Contrastive Learning on LLM Back Generation Treebank for Cross-domain Constituency Parsing

  2025cites this paper
• CACE: Sim-to-Real Indoor 3D Semantic Segmentation via Context-Aware Augmentation and Consistency Enforcement

  2025cites this paper
• PropitterX: a Twitter-based propaganda corpus extended with multiple contextual features

  2025cites this paper
• Progressive low-confidence pseudolabeling for semisupervised node classification

  2025cites this paper
• CGMatch: A Different Perspective of Semi-supervised Learning

  2025cites this paper
• Semi-Supervised Learning for Dose Prediction in Targeted Radionuclide: A Synthetic Data Study

  2025cites this paper
• Cross-Cloud Consistency for Weakly Supervised Point Cloud Semantic Segmentation

  2025cites this paper
• Semi-supervised medical image classification via distance correlation minimization and graph attention regularization

  2024cites this paper
• Cross-Domain Learning for Video Anomaly Detection with Limited Supervision

  2024cites this paper
• PL-MCT: pseudo-labeling and multi-frame consistency training for semi-supervised visual tracking

  2024cites this paper
• Named entity recognition using transfer learning and small human‐ and meta‐pseudo‐labeled datasets

  2024cites this paper
• Leveraging the Structure of Pre-trained Embeddings to Minimize Annotation Effort

  2024cites this paper
• Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale

  2024cites this paper
• Training-Free Unsupervised Prompt for Vision-Language Models

  2024cites this paper
• Hierarchical Differential Amplifier Contrastive Learning for Semi-supervised Extractive Summarization

  2024cites this paper
• A Semi-Supervised Method for Grain Boundary Segmentation: Teacher–Student Knowledge Distillation and Pseudo-Label Repair

  2024cites this paper
• Depression symptoms modelling from social media text: an LLM driven semi-supervised learning approach

  2024cites this paper
• Graph augmentation for node-level few-shot learning

  2024cites this paper
• Deep Confident Steps to New Pockets: Strategies for Docking Generalization

  2024cites this paper
• Structured Tree Alignment for Evaluation of (Speech) Constituency Parsing

  2024cites this paper
• Unsupervised Morphological Tree Tokenizer

  2024cites this paper
• Exploring Inherent Consistency for Semi-Supervised Anatomical Structure Segmentation in Medical Imaging

  2024cites this paper
• Extraction of Event Structures from Text

  2024cites this paper
• Beyond Pixels: Semi-Supervised Semantic Segmentation with a Multi-scale Patch-based Multi-Label Classifier

  2024cites this paper
• WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agents

  2024cites this paper
• Cross-domain Constituency Parsing by Leveraging Heterogeneous Data

  2024cites this paper
• Weighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentation

  2024cites this paper
• Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applications

  2023cites this paper
• ReFixMatch-LS: reusing pseudo-labels for semi-supervised skin lesion classification

  2023cites this paper
• Toolformer: Language Models Can Teach Themselves to Use Tools

  2023cites this paper
• Unsupervised domain adaptation for object detection through mixed-domain and co-training learning

  2023cites this paper
• Data-driven dependency parsing of Vedic Sanskrit

  2023cites this paper
• Exploiting Censored Information in Self-Training for Time-to-Event Prediction

  2023cites this paper
• Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity

  2023cites this paper
• Multistage Collaborative Knowledge Distillation from Large Language Models

  2023cites this paper
• Approximately Bayes-optimal pseudo-label selection

  2023cites this paper
• DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback

  2023cites this paper
• Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation

  2023cites this paper
• Student as an Inherent Denoiser of Noisy Teacher

  2023cites this paper
• SequenceMatch Revisiting the design of weak-strong augmentations for Semi-supervised learning

  2023cites this paper
• KD-Fixmatch: Knowledge Distillation Siamese Neural Networks

  2023cites this paper
• A Semi-Supervised Approach for Power System Event Identification

  2023cites this paper
• In all likelihoods: robust selection of pseudo-labeled data

  2023cites this paper
• Speech Emotion Recognition based on Semi-Supervised Adversarial Variational Autoencoder

  2023cites this paper
• MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins

  2023cites this paper
• MARRS: Modern Backbones Assisted Co-training for Rapid and Robust Semi-Supervised Domain Adaptation

  2023cites this paper
• Class-aware progressive self-training for learning convolutional networks on graphs

  2023cites this paper
• PHM-IRNET: Self-training thermal segmentation approach for thermographic inspection of industrial components

  2023cites this paper
• Data-efficient Active Learning for Structured Prediction with Partial Annotation and Self-Training

  2023cites this paper
• Progressive cross-domain knowledge distillation for efficient unsupervised domain adaptive object detection

  2023cites this paper
• Extrinsic Factors Affecting the Accuracy of Biomedical NER

  2023cites this paper
• Friend-training: Learning from Models of Different but Related Tasks

  2023cites this paper
• FixMatch-LS: Semi-supervised skin lesion classification with label smoothing

  2023cites this paper
• In all LikelihoodS: How to Reliably Select Pseudo-Labeled Data for Self-Training in Semi-Supervised Learning

  2023cites this paper
• Reducing cohort bias in natural language understanding systems with targeted self-training scheme

  2023cites this paper
• Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner

  2023cites this paper
• Self-Healing Through Error Detection, Attribution, and Retraining

  2023cites this paper
• SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples

  2023cites this paper
• Rethinking Semi-supervised Learning with Language Models

  2023cites this paper
• ASPER: Answer Set Programming Enhanced Neural Network Models for Joint Entity-Relation Extraction

  2023cites this paper
• Approximate Bayes Optimal Pseudo-Label Selection

  2023cites this paper
• Progressive Feature Upgrade in Semi-supervised Learning on Tabular Domain

  2022cites this paper
• A Semi-supervised Deep Learning Model with Consistency Regularization of Augmented Samples for Imbalanced Fault Detection

  2022cites this paper
• Source-Free Domain Adaptation for Question Answering with Masked Self-training

  2022cites this paper
• On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey

  2022cites this paper
• Zero-Label Prompt Selection

  2022cites this paper
• Weakly Supervised Training of Universal Visual Concepts for Multi-domain Semantic Segmentation

  2022cites this paper
• Predicting Survival Outcomes in the Presence of Unlabeled Data

  2022cites this paper
• Deep semi-supervised multiple instance learning with self-correction for DME classification from OCT images

  2022cites this paper
• Automatic Rule Induction for Efficient and Interpretable Semi-Supervised Learning

  2022cites this paper
• Dual-feature-embeddings-based semi-supervised learning for cognitive engagement classification in online course discussions

  2022cites this paper
• Investigating Semi-Supervised Learning Algorithms in Text Datasets

  2022cites this paper
• Improving Low-resource RRG Parsing with Cross-lingual Self-training

  2022cites this paper
• A Comparison of Strategies for Source-Free Domain Adaptation

  2022cites this paper
• Depression Symptoms Modelling from Social Media Text: A Semi-supervised Learning Approach

  2022cites this paper
• Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent

  2022influential citation
• DuIVA: An Intelligent Voice Assistant for Hands-free and Eyes-free Voice Interaction with the Baidu Maps App

  2022cites this paper
• Coordination Generation via Synchronized Text-Infilling

  2022cites this paper
• STAD: Self-Training with Ambiguous Data for Low-Resource Relation Extraction

  2022cites this paper
• Cross-domain Aspect-based Sentiment Analysis with Multimodal Sources

  2022cites this paper
• Generating unlabelled data for a tri-training approach in a low resourced NER task

  2022cites this paper
• Unsupervised Domain Adaptation for Question Generation with DomainData Selection and Self-training

  2022cites this paper
• HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization

  2022cites this paper
• Automatic Rule Induction for Efficient Semi-Supervised Learning

  2022cites this paper
• Semi-supervised Domain Adaptation for Dependency Parsing with Dynamic Matching Network

  2022cites this paper
• SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser

  2022cites this paper
• Improve Event Extraction via Self-Training with Gradient Guidance

  2022cites this paper
• Learning with Limited Text Data

  2022cites this paper
• Improving Code-Switching Dependency Parsing with Semi-Supervised Auxiliary Tasks

  2022influential citation
• Measuring Annotator Agreement Generally across Complex Structured, Multi-object, and Free-text Annotation Tasks

  2022cites this paper