Controlled Text Reduction

TL;DR

This paper introduces Controlled Text Reduction, a task focused on generating coherent summaries from pre-selected content, supported by new datasets and a baseline model for research and semi-automated summarization.

Contribution

It formalizes Controlled Text Reduction as a standalone task, creates new datasets, and develops a supervised baseline model for coherent text generation from highlighted content.

Findings

Crowdsourced high-quality datasets for the task.

Automatically generated larger training datasets from existing benchmarks.

Baseline model shows promising results and provides insights.

Abstract

Producing a reduced version of a source text, as in generic or focused summarization, inherently involves two distinct subtasks: deciding on targeted content and generating a coherent text conveying it. While some popular approaches address summarization as a single end-to-end task, prominent works support decomposed modeling for individual subtasks. Further, semi-automated text reduction is also very appealing, where users may identify targeted content while models would generate a corresponding coherent summary. In this paper, we focus on the second subtask, of generating coherent text given pre-selected content. Concretely, we formalize \textit{Controlled Text Reduction} as a standalone task, whose input is a source text with marked spans of targeted content ("highlighting"). A model then needs to generate a coherent text that includes all and only the target information. We advocate the potential of such models, both for modular fully-automatic summarization, as well as for semi-automated human-in-the-loop use cases. Facilitating proper research, we crowdsource high-quality dev and test datasets for the task. Further, we automatically generate a larger "silver" training dataset from available summarization benchmarks, leveraging a pretrained summary-source alignment model. Finally, employing these datasets, we present a supervised baseline model, showing promising results and insightful analyses.