Abstractive Query Focused Summarization with Query-Free Resources

by   Yumo Xu, et al.

The availability of large-scale datasets has driven the development of neural sequence-to-sequence models to generate generic summaries, i.e., summaries which do not correspond to any pre-specified queries. However, due to the lack of training data, query focused summarization (QFS) has been studied mainly with extractive methods. In this work, we consider the problem of leveraging only generic summarization resources to build an abstractive QFS system. We propose Marge, a Masked ROUGE Regression framework composed of a novel unified representation for summaries and queries, and a distantly supervised training task for answer evidence estimation. To further utilize generic data for generation, three attributes are incorporated during training and inference to control the shape of the final summary: evidence rank, query guidance, and summary length. Despite learning from minimal supervision, our system achieves state-of-the-art results in the distantly supervised setting across domains and query types.


page 1

page 2

page 3

page 4


Text Summarization with Latent Queries

The availability of large-scale datasets has driven the development of n...

Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance

Query focused summarization (QFS) models aim to generate summaries from ...

Transfer Learning for Abstractive Summarization at Controllable Budgets

Summarizing a document within an allocated budget while maintaining its ...

Query Focused Multi-Document Summarization with Distant Supervision

We consider the problem of better modeling query-cluster interactions to...

CLIP-It! Language-Guided Video Summarization

A generic video summary is an abridged version of a video that conveys t...

Storyboard: Optimizing Precomputed Summaries for Aggregation

An emerging class of data systems partition their data and precompute ap...