Understanding attention-based encoder-decoder networks: a case study with chess scoresheet recognition
This work provides insights into the learning dynamics of attention-based networks, which could help in better training such models, though it is incremental as it focuses on understanding rather than introducing new methods.
The paper studied encoder-decoder recurrent neural networks with attention mechanisms to understand how learning occurs in these networks, using handwritten chess scoresheet recognition as a case study, and identified competition, collaboration, and dependence relations between subtasks like input-output alignment and handwriting recognition.
Deep neural networks are largely used for complex prediction tasks. There is plenty of empirical evidence of their successful end-to-end training for a diversity of tasks. Success is often measured based solely on the final performance of the trained network, and explanations on when, why and how they work are less emphasized. In this paper we study encoder-decoder recurrent neural networks with attention mechanisms for the task of reading handwritten chess scoresheets. Rather than prediction performance, our concern is to better understand how learning occurs in these type of networks. We characterize the task in terms of three subtasks, namely input-output alignment, sequential pattern recognition, and handwriting recognition, and experimentally investigate which factors affect their learning. We identify competition, collaboration and dependence relations between the subtasks, and argue that such knowledge might help one to better balance factors to properly train a network.