526 citations · 1.1k across the 32 of their papers we have counts for
8 papers · 2 filters
What Do Recurrent Neural Network Grammars Learn About Syntax?
Adhiguna Kuncoro, Miguel Ballesteros, Lingpeng Kong +3
Recurrent neural network grammars (RNNG) are a recently proposed probabilistic generative modeling family for natural language. They show state-of-the-art language modeling and par…
Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser
Adhiguna Kuncoro, Miguel Ballesteros, Lingpeng Kong +2
We introduce two first-order graph-based dependency parsers achieving a new state of the art. The first is a consensus parser built from an ensemble of independently trained greedy…
Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs
Swabha Swayamdipta, Miguel Ballesteros, Chris Dyer +1
We present a transition-based parser that jointly produces syntactic and semantic dependencies. It learns a representation of the entire algorithm state, using stack long short-ter…
Neural Architectures for Named Entity Recognition
Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian +2
State-of-the-art named entity recognition systems rely heavily on hand-crafted features and domain-specific knowledge in order to learn effectively from the small, supervised train…
Static and Dynamic Feature Selection in Morphosyntactic Analyzers
Bernd Bohnet, Miguel Ballesteros, Ryan McDonald +1
We study the use of greedy feature selection methods for morphosyntactic tagging under a number of different conditions. We compare a static ordering of features to a dynamic order…
Training with Exploration Improves a Greedy Stack-LSTM Parser
Miguel Ballesteros, Yoav Goldberg, Chris Dyer +1
We adapt the greedy Stack-LSTM dependency parser of Dyer et al. (2015) to support a training-with-exploration procedure using dynamic oracles(Goldberg and Nivre, 2013) instead of c…