SummHelper: Collaborative Human-Computer Summarization

TL;DR

SummHelper is a collaborative summarization tool that combines automated content suggestions with user input, enabling more interactive and controllable text summarization through a two-phase process.

Contribution

It introduces a novel two-phase human-computer collaborative framework for text summarization, balancing automation with user control.

Findings

Participants appreciated the balance between automation and input.

The system improved user engagement in summarization tasks.

Small-scale studies showed effective collaboration and refinement.

Abstract

Current approaches for text summarization are predominantly automatic, with rather limited space for human intervention and control over the process. In this paper, we introduce SummHelper, a 2-phase summarization assistant designed to foster human-machine collaboration. The initial phase involves content selection, where the system recommends potential content, allowing users to accept, modify, or introduce additional selections. The subsequent phase, content consolidation, involves SummHelper generating a coherent summary from these selections, which users can then refine using visual mappings between the summary and the source text. Small-scale user studies reveal the effectiveness of our application, with participants being especially appreciative of the balance between automated guidance and opportunities for personal input.