CTRLsum: Towards Generic Controllable Text Summarization

by   Junxian He, et al.

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


page 1

page 2

page 3

page 4


EntSUM: A Data Set for Entity-Centric Summarization

Controllable summarization aims to provide summaries that take into acco...

Controllable Abstractive Summarization

Current models for document summarization ignore user preferences such a...

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

Existing abstractive summarization models lack explicit control mechanis...

Controllable Summarization with Constrained Markov Decision Process

We study controllable text summarization which allows users to gain cont...

RefSum: Refactoring Neural Summarization

Although some recent works show potential complementarity among differen...

Nutri-bullets: Summarizing Health Studies by Composing Segments

We introduce Nutri-bullets, a multi-document summarization task for heal...

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

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