Domain Adaptation for Dependency Parsing via Self-Training

This paper presents a successful approach for domain adaptation of a dependency parser via self-training. We improve parsing accuracy for out-of-domain texts with a self-training approach that uses confidence-based methods to select additional training samples. We compare two confidence-based methods: The first method uses the parse score of the employed parser to measure the confidence into a parse tree. The second method calculates the score differences between the best tree and alternative trees. With these methods, we were able to improve the labeled accuracy score by 1.6 percentage points on texts from a chemical domain and by 0.6 on average on texts of three web domains. Our improvements on the chemical texts of 1.5% UAS is substantially higher than improvements reported in previous work of 0.5% UAS. For the three web domains, no positive results for self-training have been reported before.

• Publication year

  2015

• Venue

  International Workshop/Conference on Parsing Technologies

• Publication date

  2015-07-01

• Fields of study

  Chemistry, Computer Science

• Identifiers
  DOI 10.18653/v1/w15-2201
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Exploring Options for Fast Domain Adaptation of Dependency Parsers

  2014cited by this paper
• Semi-supervised experiments at LORIA for the SPMRL 2014 Shared Task

  2014cited by this paper
• The IMS-Wrocław-Szeged-CIS Entry at the SPMRL 2014 Shared Task: Reranking and Morphosyntax Meet Unlabeled Data⇤

  2014cited by this paper
• Domain Adaptation for Parsing

  2013cited by this paper
• Joint Morphological and Syntactic Analysis for Richly Inflected Languages

  2013cited by this paper
• Semi-Supervised Feature Transformation for Dependency Parsing

  2013cited by this paper
• Experiments in Newswire-to-Law Adaptation of Graph-Based Dependency Parsers

  2012cited by this paper
• Overview of the 2012 Shared Task on Parsing the Web

  2012cited by this paper
• Are You Sure? Confidence in Prediction of Dependency Tree Edges

  2012influential reference
• DCU-Paris13 systems for the SANCL 2012 shared task

  2012cited by this paper
• Domain adaptation for parsing

  2011cited by this paper
• Exploring self training for Hindi dependency parsing

  2011cited by this paper
• Self-Training without Reranking for Parser Domain Adaptation and Its Impact on Semantic Role Labeling

  2010cited by this paper
• Semi-supervised dependency parsing using generalized tri-training

  2010cited by this paper
• The CoNLL-2009 Shared Task: Syntactic and Semantic Dependencies in Multiple Languages

  2009cited by this paper
• Simple Semi-supervised Dependency Parsing

  2008cited by this paper
• Confidence-weighted linear classification

  2008cited by this paper
• Learning Reliability of Parses for Domain Adaptation of Dependency Parsing

  2008influential reference
• Learning Reliable Information for Dependency Parsing Adaptation

  2008influential reference
• Extended Constituent-to-Dependency Conversion for English

  2007cited by this paper
• Incremental Non-Projective Dependency Parsing

  2007cited by this paper
• The CoNLL 2007 Shared Task on Dependency Parsing

  2007cited by this paper
• Self-Training for Enhancement and Domain Adaptation of Statistical Parsers Trained on Small Datasets

  2007cited by this paper
• Dependency Parsing and Domain Adaptation with LR Models and Parser Ensembles

  2007cited by this paper
• Effective Self-Training for Parsing

  2006influential reference
• Reranking and Self-Training for Parser Adaptation

  2006influential reference
• Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking

  2005cited by this paper
• Wide Coverage Parsing with Stochastic Attribute Value Grammars

  2004cited by this paper
• CLSP WS-02 Final Report: Semi-Supervised Training for Statistical Parsing

  2003cited by this paper
• Corrected Co-training for Statistical Parsers

  2003cited by this paper
• Applying Co-Training Methods to Statistical Parsing

  2001cited by this paper
• Pseudo-Projectivity, A Polynomially Parsable Non-Projective Dependency Grammar

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

  1997cited by this paper

• Fake News Classification in Urdu: A Domain Adaptation Approach for a Low-Resource Language

  2025cites this paper
• Multi-source domain adaptation for dependency parsing via domain-aware feature generation

  2024cites this paper
• LLM-Assisted Data Augmentation for Chinese Dialogue-Level Dependency Parsing

  2024cites this paper
• Cross-domain Chinese Sentence Pattern Parsing

  2024influential citation
• Curriculum-Style Fine-Grained Adaption for Unsupervised Cross-Lingual Dependency Transfer

  2023cites this paper
• LLM-enhanced Self-training for Cross-domain Constituency Parsing

  2023cites this paper
• Fine-Grained Domain Adaptation for Chinese Syntactic Processing

  2023cites this paper
• DAT-MT Accelerated Graph Fusion Dependency Parsing Model for Small Samples in Professional Fields

  2023cites this paper
• How Can Graph Neural Networks Help Document Retrieval: A Case Study on CORD19 with Concept Map Generation

  2022cites this paper
• Dependency Parsing via Sequence Generation

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

  2022cites this paper
• Explainable Misinformation Detection Across Multiple Social Media Platforms

  2022cites this paper
• Schema-Free Dependency Parsing via Sequence Generation

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

  2022cites this paper
• Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition

  2021cites this paper
• Improving Neural RST Parsing Model with Silver Agreement Subtrees

  2021cites this paper
• Unsupervised Domain Adaptation Method with Semantic-Structural Alignment for Dependency Parsing

  2021cites this paper
• A Fine-Grained Domain Adaption Model for Joint Word Segmentation and POS Tagging

  2021cites this paper
• APGN: Adversarial and Parameter Generation Networks for Multi-Source Cross-Domain Dependency Parsing

  2021cites this paper
• Tri-training for Dependency Parsing Domain Adaptation

  2021cites this paper
• Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution

  2020cites this paper
• Cross-Lingual Dependency Parsing via Self-Training

  2020cites this paper
• A Survey of Unsupervised Dependency Parsing

  2020cites this paper
• A survey of syntactic-semantic parsing based on constituent and dependency structures

  2020cites this paper
• Evaluating a Dependency Parser on DeReKo

  2020cites this paper
• Neural Unsupervised Domain Adaptation in NLP—A Survey

  2020cites this paper
• Semi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations

  2020cites this paper
• Attention-based Domain adaption Using Transfer Learning for Part-of-Speech Tagging: An Experiment on the Hindi language

  2020influential citation
• Adversarial Domain Adaptation for Chinese Semantic Dependency Graph Parsing

  2019cites this paper
• Semi-supervised Domain Adaptation for Dependency Parsing

  2019cites this paper
• Semi-Supervised Methods for Out-of-Domain Dependency Parsing

  2018influential citation
• Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examples

  2018cites this paper
• Domain Adaptation in Dependency Parsing via Transformation Based Error Driven Learning

  2018influential citation
• Cross-Domain and Semisupervised Named Entity Recognition in Chinese Social Media: A Unified Model

  2018cites this paper
• A Unified Model for Cross-Domain and Semi-Supervised Named Entity Recognition in Chinese Social Media

  2017cites this paper
• Chapter 23 PARSING

  2016cites this paper
• Dependency Language Models for Transition-based Dependency Parsing

  2016cites this paper