Transition-Based Dependency Parsing with Stack Long Short-Term Memory

Abstract

We propose a technique for learning representations of parser states in transition-based dependency parsers. Our primary innovation is a new control structure for sequence-to-sequence neural networks---the stack LSTM. Like the conventional stack data structures used in transition-based parsing, elements can be pushed to or popped from the top of the stack in constant time, but, in addition, an LSTM maintains a continuous space embedding of the stack contents. This lets us formulate an efficient parsing model that captures three facets of a parser's state: (i) unbounded look-ahead into the buffer of incoming words, (ii) the complete history of actions taken by the parser, and (iii) the complete contents of the stack of partially built tree fragments, including their internal structures. Standard backpropagation techniques are used for training and yield state-of-the-art parsing performance.

Proceedings of ACL 2015

References in corpus (1)

• Structured Training for Neural Network Transition-Based Parsing

Cited by in corpus (140)

• Recent Trends in Deep Learning Based Natural Language Processing
• The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
• DyNet: The Dynamic Neural Network Toolkit
• Massively Multilingual Word Embeddings
• End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
• Natural Language Processing Advancements By Deep Learning: A Survey
• Long Short-Term Memory-Networks for Machine Reading
• A Multi-task Approach for Named Entity Recognition in Social Media Data
• Glyce: Glyph-vectors for Chinese Character Representations
• Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
• Recurrent Dropout without Memory Loss
• Multitask Learning for Fine-Grained Twitter Sentiment Analysis
• Paradigm Shift in Natural Language Processing
• Optimizing Performance of Recurrent Neural Networks on GPUs
• Improved Transition-Based Parsing by Modeling Characters instead of Words with LSTMs
• Cross-lingual, Character-Level Neural Morphological Tagging
• Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
• A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
• Tree-structured composition in neural networks without tree-structured architectures
• Learning Continuous Semantic Representations of Symbolic Expressions
• Learning Global Features for Coreference Resolution
• Introduction to Neural Network based Approaches for Question Answering over Knowledge Graphs
• Neural Models for Sequence Chunking
• Structured Training for Neural Network Transition-Based Parsing
• Neural Probabilistic Model for Non-projective MST Parsing
• Sentence-State LSTM for Text Representation
• SyntaxNet Models for the CoNLL 2017 Shared Task
• Question Answering over Knowledge Base with Neural Attention Combining Global Knowledge Information
• Hierarchical Pointer Net Parsing
• Structured Prediction as Translation between Augmented Natural Languages
• An attentive neural architecture for joint segmentation and parsing and its application to real estate ads
• A Fast Unified Model for Parsing and Sentence Understanding
• DRAGNN: A Transition-based Framework for Dynamically Connected Neural Networks
• Visualizing and Understanding Curriculum Learning for Long Short-Term Memory Networks
• Leveraging Knowledge Bases in LSTMs for Improving Machine Reading
• Exploring Segment Representations for Neural Segmentation Models
• On-the-fly Operation Batching in Dynamic Computation Graphs
• Bidirectional Tree-Structured LSTM with Head Lexicalization
• Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling
• How Important is Syntactic Parsing Accuracy? An Empirical Evaluation on Rule-Based Sentiment Analysis
• Sentence Pair Scoring: Towards Unified Framework for Text Comprehension
• Data Recombination for Neural Semantic Parsing
• RP-DNN: A Tweet level propagation context based deep neural networks for early rumor detection in Social Media
• Deriving Neural Architectures from Sequence and Graph Kernels
• Training with Exploration Improves a Greedy Stack-LSTM Parser
• Learning to Parse and Translate Improves Neural Machine Translation
• Learning Crosslingual Word Embeddings without Bilingual Corpora
• Are Emojis Predictable?
• Learning Structured Natural Language Representations for Semantic Parsing
• Exploiting Multi-typed Treebanks for Parsing with Deep Multi-task Learning
• Fact-based Text Editing
• Bi-directional Attention with Agreement for Dependency Parsing
• Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning
• Transfer Learning for Neural Semantic Parsing
• A* CCG Parsing with a Supertag and Dependency Factored Model
• Top-down Tree Long Short-Term Memory Networks
• Adversarial Learning for Chinese NER from Crowd Annotations
• Deep Recurrent Neural Networks for Product Attribute Extraction in eCommerce
• Contrastive Learning of Emoji-based Representations for Resource-Poor Languages
• A Bayesian Model for Generative Transition-based Dependency Parsing
• Can LSTM Learn to Capture Agreement? The Case of Basque
• Keystroke dynamics as signal for shallow syntactic parsing
• Emotions are Universal: Learning Sentiment Based Representations of Resource-Poor Languages using Siamese Networks
• Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles
• Recursive Subtree Composition in LSTM-Based Dependency Parsing
• Incremental Natural Language Processing: Challenges, Strategies, and Evaluation
• A Simple LSTM model for Transition-based Dependency Parsing
• Incremental Parsing with Minimal Features Using Bi-Directional LSTM
• A Generative Parser with a Discriminative Recognition Algorithm
• Learning Over Long Time Lags
• Scene Graph Parsing as Dependency Parsing
• A Neural Transition-based Model for Nested Mention Recognition
• LSTM Easy-first Dependency Parsing with Pre-trained Word Embeddings and Character-level Word Embeddings in Vietnamese
• Word Sense Disambiguation with LSTM: Do We Really Need 100 Billion Words?
• An empirical study for Vietnamese dependency parsing
• Broad-Coverage Semantic Parsing as Transduction
• On the relation between dependency distance, crossing dependencies, and parsing. Comment on "Dependency distance: a new perspective on syntactic patterns in natural languages" by Haitao Liu et al
• Dependency Parsing as Head Selection
• Top-down Tree Structured Decoding with Syntactic Connections for Neural Machine Translation and Parsing
• Visual Attention Model for Cross-sectional Stock Return Prediction and End-to-End Multimodal Market Representation Learning
• Fast and Accurate Neural Word Segmentation for Chinese
• A Chinese Dataset with Negative Full Forms for General Abbreviation Prediction
• Read, Tag, and Parse All at Once, or Fully-neural Dependency Parsing
• Distilling Knowledge for Search-based Structured Prediction
• Reading Comprehension using Entity-based Memory Network
• Joint Learning of Named Entity Recognition and Entity Linking
• Universal Dependencies Parsing for Colloquial Singaporean English
• Scalable Syntax-Aware Language Models Using Knowledge Distillation
• An Empirical Investigation of Global and Local Normalization for Recurrent Neural Sequence Models Using a Continuous Relaxation to Beam Search
• Weakly-supervised Neural Semantic Parsing with a Generative Ranker
• Multi-task Domain Adaptation for Sequence Tagging
• Neural Architectures for Named Entity Recognition
• Dependency Grammar Induction with a Neural Variational Transition-based Parser
• Contextualized End-to-End Neural Entity Linking
• Dependency Parsing with LSTMs: An Empirical Evaluation
• How Do Source-side Monolingual Word Embeddings Impact Neural Machine Translation?
• A Survey on Semantic Parsing from the perspective of Compositionality
• Learning an Executable Neural Semantic Parser
• Shift-Reduce Constituent Parsing with Neural Lookahead Features
• Neural Particle Smoothing for Sampling from Conditional Sequence Models
• Stack-propagation: Improved Representation Learning for Syntax
• Tackling Sequence to Sequence Mapping Problems with Neural Networks
• In-Order Transition-based Constituent Parsing
• An Effective Transition-based Model for Discontinuous NER
• AI Marker-based Large-scale AI Literature Mining
• Effective Batching for Recurrent Neural Network Grammars
• Transition-Based Dependency Parsing using Perceptron Learner
• An Investigation of the Interactions Between Pre-Trained Word Embeddings, Character Models and POS Tags in Dependency Parsing
• A Hierarchical Deep Learning Natural Language Parser for Fashion
• Cross-Lingual Task-Specific Representation Learning for Text Classification in Resource Poor Languages
• Non-Projective Dependency Parsing via Latent Heads Representation (LHR)
• Viable Dependency Parsing as Sequence Labeling
• Parallelizable Stack Long Short-Term Memory
• Dependency Language Models for Transition-based Dependency Parsing
• Encoder-Decoder Shift-Reduce Syntactic Parsing
• Hierarchical Hidden Markov Jump Processes for Cancer Screening Modeling
• Cavs: A Vertex-centric Programming Interface for Dynamic Neural Networks
• Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing
• Research on multi-dimensional end-to-end phrase recognition algorithm based on background knowledge
• Concurrent Parsing of Constituency and Dependency
• Technical notes: Syntax-aware Representation Learning With Pointer Networks
• Improving Neural Sequence Labelling using Additional Linguistic Information
• Semi-Supervised Methods for Out-of-Domain Dependency Parsing
• An AMR Aligner Tuned by Transition-based Parser
• Context-Aware Prediction of Derivational Word-forms
• AMR-to-Text Generation with Cache Transition Systems
• Joint Parsing and Generation for Abstractive Summarization
• LSTMs Compose (and Learn) Bottom-Up
• A Search-based Neural Model for Biomedical Nested and Overlapping Event Detection
• Focused Contrastive Training for Test-based Constituency Analysis
• Semi-supervised Autoencoding Projective Dependency Parsing
• Few-Shot Semantic Parsing for New Predicates
• In-Order Chart-Based Constituent Parsing
• NameRec*: Highly Accurate and Fine-grained Person Name Recognition
• Research on Annotation Rules and Recognition Algorithm Based on Phrase Window
• On Multilingual Training of Neural Dependency Parsers
• ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network
• Transition-based Parsing with Context Enhancement and Future Reward Reranking
• Topic Spotting using Hierarchical Networks with Self Attention
• Hybrid Oracle: Making Use of Ambiguity in Transition-based Chinese Dependency Parsing