Improving Long Text Understanding with Knowledge Distilled from Summarization Model

TL;DR

This paper introduces Gist Detector, a method that leverages summarization models to extract key information from long texts, significantly improving performance across various NLP tasks.

Contribution

The paper presents a novel Gist Detector that distills gist detection knowledge from summarization models to enhance long text understanding in downstream tasks.

Findings

Significant performance improvements on long document classification.

Enhanced accuracy in open-domain question answering.

Improved results in non-parallel text style transfer.

Abstract

Long text understanding is important yet challenging for natural language processing. A long article or document usually contains many redundant words that are not pertinent to its gist and sometimes can be regarded as noise. With recent advances of abstractive summarization, we propose our \emph{Gist Detector} to leverage the gist detection ability of a summarization model and integrate the extracted gist into downstream models to enhance their long text understanding ability. Specifically, Gist Detector first learns the gist detection knowledge distilled from a summarization model, and then produces gist-aware representations to augment downstream models. We evaluate our method on three different tasks: long document classification, distantly supervised open-domain question answering, and non-parallel text style transfer. The experimental results show that our method can significantly improve the performance of baseline models on all tasks.