PREME: Preference-based Meeting Exploration through an Interactive Questionnaire

TL;DR

This paper introduces PREME, an innovative framework that creates interactive questionnaires to help users explore meeting content based on their preferences, addressing the challenge of managing large volumes of online meetings.

Contribution

It presents a new end-to-end system for generating preference-based questionnaires and an automatic evaluation method for assessing question quality and coverage.

Findings

Generated questionnaires are answerable and factually correct.

The system effectively covers key meeting content.

Provides a new approach for meeting content exploration.

Abstract

The recent increase in the volume of online meetings necessitates automated tools for managing and organizing the material, especially when an attendee has missed the discussion and needs assistance in quickly exploring it. In this work, we propose a novel end-to-end framework for generating interactive questionnaires for preference-based meeting exploration. As a result, users are supplied with a list of suggested questions reflecting their preferences. Since the task is new, we introduce an automatic evaluation strategy. Namely, it measures how much the generated questions via questionnaire are answerable to ensure factual correctness and covers the source meeting for the depth of possible exploration.