At Google, we spend a lot of time thinking about how computer systems can read and understandhuman language in order to process it in intelligent ways. Today, we are excited to share the fruits of our research with the broader community by releasing SyntaxNet, an open-source neural network framework implemented in TensorFlow that provides a foundation for Natural Language Understanding (NLU) systems. Our release includes all the code needed to train new SyntaxNet models on your own data, as well as Parsey McParseface, an English parser that we have trained for you and that you can use to analyze English text.
READ MORE ON GOOGLE RESEARCH BLOG
Ref: Globally Normalized Transition-Based Neural Networks. arXiv - Computation and Language (19 March 2016) | arXiv:1603.06042 | PDF
ABSTRACT
We introduce a globally normalized transition-based neural network model that achieves state-of-the-art part-ofspeech tagging, dependency parsing and sentence compression results. Our model is a simple feed-forward neural network that operates on a task-specific transition system, yet achieves comparable or better accuracies than recurrent models. The key insight is based on a novel proof illustrating the label bias problem and showing that globally normalized models can be strictly more expressive than locally normalized models.
