CTRLsum: Towards Generic Controllable Text Summarization

12/08/2020
by   Junxian He, et al.
0

Current summarization systems yield generic summaries that are disconnected from users' preferences and expectations. To address this limitation, we present CTRLsum, a novel framework for controllable summarization. Our approach enables users to control multiple aspects of generated summaries by interacting with the summarization system through textual input in the form of a set of keywords or descriptive prompts. Using a single unified model, CTRLsum is able to achieve a broad scope of summary manipulation at inference time without requiring additional human annotations or pre-defining a set of control aspects during training. We quantitatively demonstrate the effectiveness of our approach on three domains of summarization datasets and five control aspects: 1) entity-centric and 2) length-controllable summarization, 3) contribution summarization on scientific papers, 4) invention purpose summarization on patent filings, and 5) question-guided summarization on news articles in a reading comprehension setting. Moreover, when used in a standard, uncontrolled summarization setting, CTRLsum achieves state-of-the-art results on the CNN/DailyMail dataset. Code and model checkpoints are available at https://github.com/salesforce/ctrl-sum

READ FULL TEXT

page 1

page 2

page 3

page 4

04/05/2022

EntSUM: A Data Set for Entity-Centric Summarization

Controllable summarization aims to provide summaries that take into acco...
11/14/2017

Controllable Abstractive Summarization

Current models for document summarization ignore user preferences such a...
10/08/2021

HydraSum – Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models

Existing abstractive summarization models lack explicit control mechanis...
08/07/2021

Controllable Summarization with Constrained Markov Decision Process

We study controllable text summarization which allows users to gain cont...
04/15/2021

RefSum: Refactoring Neural Summarization

Although some recent works show potential complementarity among differen...
03/22/2021

Nutri-bullets: Summarizing Health Studies by Composing Segments

We introduce Nutri-bullets, a multi-document summarization task for heal...
04/29/2020

Conditional Neural Generation using Sub-Aspect Functions for Extractive News Summarization

Much progress has been made in text summarization, fueled by neural arch...