Globally Normalized Transition-Based Neural Networks
This addresses the label bias problem in natural language processing tasks, offering a more expressive model for researchers and practitioners, though it is incremental as it builds on existing transition-based approaches.
The paper tackled the problem of part-of-speech tagging, dependency parsing, and sentence compression by introducing a globally normalized transition-based neural network model, achieving state-of-the-art results with comparable or better accuracies than recurrent models.
We introduce a globally normalized transition-based neural network model that achieves state-of-the-art part-of-speech 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. We discuss the importance of global as opposed to local normalization: a key insight is that the label bias problem implies that globally normalized models can be strictly more expressive than locally normalized models.