CTRLsum: Towards Generic Controllable Text Summarization
This work addresses the problem of generating generic summaries for users who need summaries tailored to specific preferences, offering a unified model that supports broad summary manipulation without extra annotations.
This paper introduces CTRLsum, a framework for controllable text summarization that allows users to guide summary generation using keywords or prompts. The system achieves state-of-the-art results on the CNN/DailyMail dataset in an uncontrolled setting and demonstrates effectiveness across three domains and five control aspects, including entity-centric and length-controllable summarization.
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