Joint POS Tagging and Transition-based Constituent Parsing in Chinese with Non-local Features

We propose three improvements to address the drawbacks of state-of-the-art transition-based constituent parsers. First, to resolve the error propagation problem of the traditional pipeline approach, we incorporate POS tagging into the syntactic parsing process. Second, to alleviate the negative influence of size differences among competing action sequences, we align parser states during beam-search decoding. Third, to enhance the power of parsing models, we enlarge the feature set with non-local features and semisupervised word cluster features. Experimental results show that these modifications improve parsing performance significantly. Evaluated on the Chinese TreeBank (CTB), our final performance reaches 86.3% (F1) when trained on CTB 5.1, and 87.1% when trained on CTB 6.0, and these results outperform all state-of-the-art parsers.

• Publication year

  2014

• Venue

  Annual Meeting of the Association for Computational Linguistics

• Publication date

  2014-06-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.3115/v1/P14-1069
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Chinese Parsing Exploiting Characters

  2013cited by this paper
• Fast and Accurate Shift-Reduce Constituent Parsing

  2013influential reference
• An Empirical Examination of Challenges in Chinese Parsing

  2013cited by this paper
• Handbook of Natural Language Processing and Machine Translation: DARPA Global Autonomous Language Exploitation

  2011cited by this paper
• Incremental Joint POS Tagging and Dependency Parsing in Chinese

  2011influential reference
• Parse Reranking Based on Higher-Order Lexical Dependencies

  2011cited by this paper
• Self-Training PCFG Grammars with Latent Annotations Across Languages

  2009influential reference
• Chinese Statistical Parsing

  2009cited by this paper
• Transition-Based Parsing of the Chinese Treebank using a Global Discriminative Model

  2009influential reference
• Simple Semi-supervised Dependency Parsing

  2008influential reference
• Forest Reranking: Discriminative Parsing with Non-Local Features

  2008cited by this paper
• Improved Inference for Unlexicalized Parsing

  2007cited by this paper
• A Fast, Accurate Deterministic Parser for Chinese

  2006cited by this paper
• Learning Accurate, Compact, and Interpretable Tree Annotation

  2006cited by this paper
• A Classifier-Based Parser with Linear Run-Time Complexity

  2005cited by this paper
• The Penn Chinese TreeBank: Phrase structure annotation of a large corpus

  2005influential reference
• Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking

  2005influential reference
• Semi-Supervised Learning for Natural Language

  2005cited by this paper
• Name Tagging with Word Clusters and Discriminative Training

  2004cited by this paper
• Incremental Parsing with the Perceptron Algorithm

  2004cited by this paper
• Head-Driven Statistical Models for Natural Language Parsing

  2003cited by this paper
• A Maximum-Entropy-Inspired Parser

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

  2000influential reference
• Improve Chinese Parsing with MaxEnt Reranking Parser

  year unknowncited by this paper

• A Coarse-to-Fine Labeling Framework for Joint Word Segmentation, POS Tagging, and Constituent Parsing

  2021cites this paper
• A survey of syntactic-semantic parsing based on constituent and dependency structures

  2020cites this paper
• Chinese Syntax Parsing Based on Sliding Match of Semantic String

  2019influential citation
• Establishing Strong Baselines for the New Decade: Sequence Tagging, Syntactic and Semantic Parsing with BERT

  2019influential citation
• Neural Ranking Models for Temporal Dependency Structure Parsing

  2018cites this paper
• We look forward to a great workshop in New Orleans !

  2018cites this paper
• Improving Sequence-to-Sequence Constituency Parsing

  2018cites this paper
• Boundary Recognition of Light-Pause Marks via Grammar Testing Method

  2018cites this paper
• From Question to Text

  2018cites this paper
• Indonesian Shift-Reduce Constituency Parser Using Feature Templates & Beam Search Strategy

  2018cites this paper
• Transition-Based Chinese AMR Parsing

  2018cites this paper
• Two Local Models for Neural Constituent Parsing

  2018cites this paper
• Straight to the Tree: Constituency Parsing with Neural Syntactic Distance

  2018cites this paper
• Detecting Syntactic Features of Translated Chinese

  2018cites this paper
• Non-Deterministic Segmentation for Chinese Lattice Parsing

  2017influential citation
• Segmenting Chinese Microtext: Joint Informal-Word Detection and Segmentation with Neural Networks

  2017cites this paper
• Building a Treebank for Vietnamese Syntactic Parsing

  2017cites this paper
• Improving Feature-Rich Transition-Based Constituent Parsing Using Recurrent Neural Networks

  2017cites this paper
• Translation Divergences in Chinese–English Machine Translation: An Empirical Investigation

  2017cites this paper
• Joint POS Tagging and Dependence Parsing With Transition-Based Neural Networks

  2017cites this paper
• Automatically Acquired Lexical Knowledge Improves Japanese Joint Morphological and Dependency Analysis

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

  2017influential citation
• Chinese POS Tagging with Attention-Based Long Short-Term Memory Network

  2017cites this paper
• Deep Learning in Lexical Analysis and Parsing

  2017cites this paper
• A Novel Neural Network Model for Joint POS Tagging and Graph-based Dependency Parsing

  2017cites this paper
• In-Order Transition-based Constituent Parsing

  2017influential citation
• Indonesian shift-reduce constituent parser

  2016cites this paper
• Stack-propagation: Improved Representation Learning for Syntax

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

  2016cites this paper
• Shift-Reduce Constituent Parsing with Neural Lookahead Features

  2016influential citation
• Enhancing Shift-Reduce Constituent Parsing with Action N-Gram Model

  2016cites this paper
• Improved Joint Kazakh POS Tagging and Chunking

  2016cites this paper
• CoNLL 2016 Shared Task on Multilingual Shallow Discourse Parsing

  2016cites this paper
• Recurrent Neural Network Grammars

  2016influential citation
• Transition-Based Left-Corner Parsing for Identifying PTB-Style Nonlocal Dependencies

  2016influential citation
• Shift-Reduce Constituency Parsing with Dynamic Programming and POS Tag Lattice

  2015influential citation
• POS tagging of Chinese Buddhist texts using Recurrent Neural Networks

  2015cites this paper
• Feature Optimization for Constituent Parsing via Neural Networks

  2015cites this paper
• Optimal Shift-Reduce Constituent Parsing with Structured Perceptron

  2015influential citation
• Randomized Greedy Inference for Joint Segmentation, POS Tagging and Dependency Parsing

  2015cites this paper
• Transition-based Neural Constituent Parsing

  2015influential citation
• MIT Open Access Articles Randomized greedy inference for joint segmentation, POS tagging and dependency parsing

  year unknowncites this paper