Goal-Driven Sequential Data Abstraction
This work addresses the need for flexible abstraction in machine intelligence and summarization applications, though it appears incremental as it builds on existing reinforcement learning methods.
The authors tackled the problem of automatic data abstraction for sequential data by proposing a goal-driven reinforcement learning framework that does not require human examples, achieving promising results across sketch, video, and text domains.
Automatic data abstraction is an important capability for both benchmarking machine intelligence and supporting summarization applications. In the former one asks whether a machine can `understand' enough about the meaning of input data to produce a meaningful but more compact abstraction. In the latter this capability is exploited for saving space or human time by summarizing the essence of input data. In this paper we study a general reinforcement learning based framework for learning to abstract sequential data in a goal-driven way. The ability to define different abstraction goals uniquely allows different aspects of the input data to be preserved according to the ultimate purpose of the abstraction. Our reinforcement learning objective does not require human-defined examples of ideal abstraction. Importantly our model processes the input sequence holistically without being constrained by the original input order. Our framework is also domain agnostic -- we demonstrate applications to sketch, video and text data and achieve promising results in all domains.