EASE: Extractive-Abstractive Summarization with Explanations

by   Haoran Li, et al.

Current abstractive summarization systems outperform their extractive counterparts, but their widespread adoption is inhibited by the inherent lack of interpretability. To achieve the best of both worlds, we propose EASE, an extractive-abstractive framework for evidence-based text generation and apply it to document summarization. We present an explainable summarization system based on the Information Bottleneck principle that is jointly trained for extraction and abstraction in an end-to-end fashion. Inspired by previous research that humans use a two-stage framework to summarize long documents (Jing and McKeown, 2000), our framework first extracts a pre-defined amount of evidence spans as explanations and then generates a summary using only the evidence. Using automatic and human evaluations, we show that explanations from our framework are more relevant than simple baselines, without substantially sacrificing the quality of the generated summary.


End-to-end Semantics-based Summary Quality Assessment for Single-document Summarization

ROUGE is the de facto criterion for summarization research. However, its...

Unsupervised Abstractive Summarization of Bengali Text Documents

Abstractive summarization systems generally rely on large collections of...

Hybrid MemNet for Extractive Summarization

Extractive text summarization has been an extensive research problem in ...

Leveraging Information Bottleneck for Scientific Document Summarization

This paper presents an unsupervised extractive approach to summarize sci...

KLearn: Background Knowledge Inference from Summarization Data

The goal of text summarization is to compress documents to the relevant ...

Deep Communicating Agents for Abstractive Summarization

We present deep communicating agents in an encoder-decoder architecture ...

BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle

The principle of the Information Bottleneck (Tishby et al. 1999) is to p...