DeepAI AI Chat
Log In Sign Up

Reinforced Extractive Summarization with Question-Focused Rewards

05/25/2018
by   Kristjan Arumae, et al.
0

We investigate a new training paradigm for extractive summarization. Traditionally, human abstracts are used to derive goldstandard labels for extraction units. However, the labels are often inaccurate, because human abstracts and source documents cannot be easily aligned at the word level. In this paper we convert human abstracts to a set of Cloze-style comprehension questions. System summaries are encouraged to preserve salient source content useful for answering questions and share common words with the abstracts. We use reinforcement learning to explore the space of possible extractive summaries and introduce a question-focused reward function to promote concise, fluent, and informative summaries. Our experiments show that the proposed method is effective. It surpasses state-of-the-art systems on the standard summarization dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/04/2019

Guiding Extractive Summarization with Question-Answering Rewards

Highlighting while reading is a natural behavior for people to track sal...
07/01/2021

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

The growth of online consumer health questions has led to the necessity ...
05/10/2021

Improving Factual Consistency of Abstractive Summarization via Question Answering

A commonly observed problem with the state-of-the art abstractive summar...
12/19/2022

Inverse Reinforcement Learning for Text Summarization

Current state-of-the-art summarization models are trained with either ma...
06/01/2021

Question-aware Transformer Models for Consumer Health Question Summarization

Searching for health information online is becoming customary for more a...
01/31/2021

Contextualized Rewriting for Text Summarization

Extractive summarization suffers from irrelevance, redundancy and incohe...
03/16/2022

A Feasibility Study of Answer-Agnostic Question Generation for Education

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