Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles
arXiv:1612.06475
Abstract
Parsing accuracy using efficient greedy transition systems has improved dramatically in recent years thanks to neural networks. Despite striking results in dependency parsing, however, neural models have not surpassed state-of-the-art approaches in constituency parsing. To remedy this, we introduce a new shift-reduce system whose stack contains merely sentence spans, represented by a bare minimum of LSTM features. We also design the first provably optimal dynamic oracle for constituency parsing, which runs in amortized O(1) time, compared to O(n^3) oracles for standard dependency parsing. Training with this oracle, we achieve the best F1 scores on both English and French of any parser that does not use reranking or external data.
EMNLP 2016
References in corpus (6)
- Improving neural networks by preventing co-adaptation of feature detectors
- ADADELTA: An Adaptive Learning Rate Method
- Transition-Based Dependency Parsing with Stack Long Short-Term Memory
- Improved Transition-Based Parsing by Modeling Characters instead of Words with LSTMs
- Structured Training for Neural Network Transition-Based Parsing
- Training with Exploration Improves a Greedy Stack-LSTM Parser
Cited by in corpus (7)
- The Marginal Value of Adaptive Gradient Methods in Machine Learning
- IncSQL: Training Incremental Text-to-SQL Parsers with Non-Deterministic Oracles
- Abstract Syntax Networks for Code Generation and Semantic Parsing
- Disentangling Adaptive Gradient Methods from Learning Rates
- Multi-task Domain Adaptation for Sequence Tagging
- Straight to the Tree: Constituency Parsing with Neural Syntactic Distance
- In-Order Transition-based Constituent Parsing