DRAGNN: A Transition-based Framework for Dynamically Connected Neural Networks
This work addresses the need for modular and dynamic neural network frameworks in natural language processing, offering incremental improvements over existing methods like seq2seq with attention.
The authors tackled the problem of constructing flexible recurrent neural architectures by introducing DRAGNN, a framework using Transition Based Recurrent Units (TBRUs) that dynamically build network connections, resulting in significantly more accurate and efficient performance for syntactic dependency parsing and improved multi-task learning for extractive summarization tasks.
In this work, we present a compact, modular framework for constructing novel recurrent neural architectures. Our basic module is a new generic unit, the Transition Based Recurrent Unit (TBRU). In addition to hidden layer activations, TBRUs have discrete state dynamics that allow network connections to be built dynamically as a function of intermediate activations. By connecting multiple TBRUs, we can extend and combine commonly used architectures such as sequence-to-sequence, attention mechanisms, and re-cursive tree-structured models. A TBRU can also serve as both an encoder for downstream tasks and as a decoder for its own task simultaneously, resulting in more accurate multi-task learning. We call our approach Dynamic Recurrent Acyclic Graphical Neural Networks, or DRAGNN. We show that DRAGNN is significantly more accurate and efficient than seq2seq with attention for syntactic dependency parsing and yields more accurate multi-task learning for extractive summarization tasks.