APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning

TL;DR

APRIL introduces an interactive summarization approach that combines active preference learning and reinforcement learning to efficiently learn user preferences without relying on reference summaries.

Contribution

It presents a novel objective function that reduces sample complexity by integrating active learning, preference learning, and reinforcement learning techniques.

Findings

Significantly reduces the number of interactions needed for learning.

Outperforms existing preference-based summarization methods.

Effective in both simulation and real-user experiments.

Abstract

We propose a method to perform automatic document summarisation without using reference summaries. Instead, our method interactively learns from users' preferences. The merit of preference-based interactive summarisation is that preferences are easier for users to provide than reference summaries. Existing preference-based interactive learning methods suffer from high sample complexity, i.e. they need to interact with the oracle for many rounds in order to converge. In this work, we propose a new objective function, which enables us to leverage active learning, preference learning and reinforcement learning techniques in order to reduce the sample complexity. Both simulation and real-user experiments suggest that our method significantly advances the state of the art. Our source code is freely available at https://github.com/UKPLab/emnlp2018-april.