Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations

Abstract

We present a simple and effective scheme for dependency parsing which is based on bidirectional-LSTMs (BiLSTMs). Each sentence token is associated with a BiLSTM vector representing the token in its sentential context, and feature vectors are constructed by concatenating a few BiLSTM vectors. The BiLSTM is trained jointly with the parser objective, resulting in very effective feature extractors for parsing. We demonstrate the effectiveness of the approach by applying it to a greedy transition-based parser as well as to a globally optimized graph-based parser. The resulting parsers have very simple architectures, and match or surpass the state-of-the-art accuracies on English and Chinese.

References in corpus (5)

• Transition-Based Dependency Parsing with Stack Long Short-Term Memory
• Natural Language Understanding with Distributed Representation
• Structured Training for Neural Network Transition-Based Parsing
• Training with Exploration Improves a Greedy Stack-LSTM Parser
• A Re-ranking Model for Dependency Parser with Recursive Convolutional Neural Network

Cited by in corpus (27)

• Natural Language Processing Advancements By Deep Learning: A Survey
• Glyce: Glyph-vectors for Chinese Character Representations
• Neural Probabilistic Model for Non-projective MST Parsing
• Robust Multilingual Part-of-Speech Tagging via Adversarial Training
• A Minimal Span-Based Neural Constituency Parser
• A Sequential Model for Classifying Temporal Relations between Intra-Sentence Events
• Scene Graph Parsing by Attention Graph
• Incremental Parsing with Minimal Features Using Bi-Directional LSTM
• A Simple LSTM model for Transition-based Dependency Parsing
• Incremental Natural Language Processing: Challenges, Strategies, and Evaluation
• Tools and resources for Romanian text-to-speech and speech-to-text applications
• LSTM Easy-first Dependency Parsing with Pre-trained Word Embeddings and Character-level Word Embeddings in Vietnamese
• Dependency Parsing as Head Selection
• Read, Tag, and Parse All at Once, or Fully-neural Dependency Parsing
• The Best of Both Worlds: Lexical Resources To Improve Low-Resource Part-of-Speech Tagging
• Analysis Methods in Neural Language Processing: A Survey
• Dependency Parsing with LSTMs: An Empirical Evaluation
• Cross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages
• A Neural Network Based Explainable Recommender System
• Dependency Grammar Induction with a Neural Variational Transition-based Parser
• Parallelizable Stack Long Short-Term Memory
• Transition-based Parsing with Lighter Feed-Forward Networks
• Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing
• An Investigation of the Interactions Between Pre-Trained Word Embeddings, Character Models and POS Tags in Dependency Parsing
• Semi-supervised Autoencoding Projective Dependency Parsing
• Parameter sharing between dependency parsers for related languages
• On Multilingual Training of Neural Dependency Parsers