Read, Tag, and Parse All at Once, or Fully-neural Dependency Parsing
arXiv:1609.03441
Abstract
We present a dependency parser implemented as a single deep neural network that reads orthographic representations of words and directly generates dependencies and their labels. Unlike typical approaches to parsing, the model doesn't require part-of-speech (POS) tagging of the sentences. With proper regularization and additional supervision achieved with multitask learning we reach state-of-the-art performance on Slavic languages from the Universal Dependencies treebank: with no linguistic features other than characters, our parser is as accurate as a transition- based system trained on perfect POS tags.
References in corpus (16)
- Efficient Estimation of Word Representations in Vector Space
- Sequence to Sequence Learning with Neural Networks
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Practical Bayesian Optimization of Machine Learning Algorithms
- ADADELTA: An Adaptive Learning Rate Method
- On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
- Theano: new features and speed improvements
- Exploring the Limits of Language Modeling
- Transition-Based Dependency Parsing with Stack Long Short-Term Memory
- End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results
- Grammar as a Foreign Language
- Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation
- Blocks and Fuel: Frameworks for deep learning
- Improved Transition-Based Parsing by Modeling Characters instead of Words with LSTMs
- Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
- SyntaxNet Models for the CoNLL 2017 Shared Task