Learning-to-Learn Agent Adaptation Policy for Abstractive Summarization

Hongzhang Mu, Tingwen Liu, Hongbo Xu

Abstract: Neural abstractive text summarization models have gained a lot of popularity. Recent researches on this tasks resort to a single generative model to generate high-quality summaries. However, people adopt adaptive strategies in the process of obtaining text abstracts, such as searching for combinations from textbooks or abstracts from domain knowledge. In this paper, we use dynamic reasoning to address abstractive summarization tasks. To achieve dynamic reasoning for high flexibility when faced with diverse summarizations, we propose a Learning-to-Learn Agent Adaption policy (LLAA-Policy) network to seamlessly adapt the selection over generative agent and retrieval agent, guided by the final summarization reward. Extensive experiments on the TT News Corpus dataset demonstrate the superiority of LLAA-Policy model over previous methods and the automatically learned policy reveals the underlying summarization aspects.