PLANTS: A Novel Problem and Dataset for Summarization of Planning-Like (PL) Tasks

TL;DR

This paper introduces a new problem and dataset for summarizing planning-like tasks, which involve generating action sequences for goal achievement, aiming to improve practical decision-making tools.

Contribution

It presents a novel plan summarization problem, a new dataset, and baseline methods, encouraging further research in this underexplored area of summarization.

Findings

Baseline methods and large language models produce varying summary quality.

Quantitative metrics and user studies validate the proposed approach.

The dataset and problem formulation open new research directions in summarization.

Abstract

Text summarization is a well-studied problem that deals with deriving insights from unstructured text consumed by humans, and it has found extensive business applications. However, many real-life tasks involve generating a series of actions to achieve specific goals, such as workflows, recipes, dialogs, and travel plans. We refer to them as planning-like (PL) tasks noting that the main commonality they share is control flow information. which may be partially specified. Their structure presents an opportunity to create more practical summaries to help users make quick decisions. We investigate this observation by introducing a novel plan summarization problem, presenting a dataset, and providing a baseline method for generating PL summaries. Using quantitative metrics and qualitative user studies to establish baselines, we evaluate the plan summaries from our method and large language models. We believe the novel problem and dataset can reinvigorate research in summarization, which some consider as a solved problem.