DeepAI AI Chat
Log In Sign Up

Guiding Extractive Summarization with Question-Answering Rewards

by   Kristjan Arumae, et al.
University of Central Florida

Highlighting while reading is a natural behavior for people to track salient content of a document. It would be desirable to teach an extractive summarizer to do the same. However, a major obstacle to the development of a supervised summarizer is the lack of ground-truth. Manual annotation of extraction units is cost-prohibitive, whereas acquiring labels by automatically aligning human abstracts and source documents can yield inferior results. In this paper we describe a novel framework to guide a supervised, extractive summarization system with question-answering rewards. We argue that quality summaries should serve as a document surrogate to answer important questions, and such question-answer pairs can be conveniently obtained from human abstracts. The system learns to promote summaries that are informative, fluent, and perform competitively on question-answering. Our results compare favorably with those reported by strong summarization baselines as evaluated by automatic metrics and human assessors.


page 1

page 2

page 3

page 4


Reinforced Extractive Summarization with Question-Focused Rewards

We investigate a new training paradigm for extractive summarization. Tra...

Question-Driven Summarization of Answers to Consumer Health Questions

Automatic summarization of natural language is a widely studied area in ...

A Feasibility Study of Answer-Agnostic Question Generation for Education

We conduct a feasibility study into the applicability of answer-agnostic...

FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization

Neural abstractive summarization models are prone to generate content in...

Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards

The growth of online consumer health questions has led to the necessity ...

Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering

We address the problem of extractive question answering using document-l...

Question Answering as an Automatic Evaluation Metric for News Article Summarization

Recent work in the field of automatic summarization and headline generat...