Scaffolding Networks: Incremental Learning and Teaching Through Questioning
arXiv:1702.08653
Abstract
We introduce a new paradigm of learning for reasoning, understanding, and prediction, as well as the scaffolding network to implement this paradigm. The scaffolding network embodies an incremental learning approach that is formulated as a teacher-student network architecture to teach machines how to understand text and do reasoning. The key to our computational scaffolding approach is the interactions between the teacher and the student through sequential questioning. The student observes each sentence in the text incrementally, and it uses an attention-based neural net to discover and register the key information in relation to its current memory. Meanwhile, the teacher asks questions about the observed text, and the student network gets rewarded by correctly answering these questions. The entire network is updated continually using reinforcement learning. Our experimental results on synthetic and real datasets show that the scaffolding network not only outperforms state-of-the-art methods but also learns to do reasoning in a scalable way even with little human generated input.
arXiv comment11 pages + Abstract + 3 figures
References in corpus (7)
- Reasoning about Entailment with Neural Attention
- Tracking the World State with Recurrent Entity Networks
- Learning to Compose Neural Networks for Question Answering
- Dialog-based Language Learning
- Query-Reduction Networks for Question Answering
- Gated End-to-End Memory Networks
- Link Prediction using Embedded Knowledge Graphs