PREME: Preference-based Meeting Exploration through an Interactive Questionnaire

Findings of the Association for Computational Linguistics: EACL 2023, pages 331–342 May 2-6, 2023 ©2023 Association for Computational Linguistics PREME: Preference-based Meeting Exploration through an Interactive Questionnaire Negar Arabzadeh University of Waterloo narabzad@uwaterloo.ca Julia Kiseleva Microsoft Research Ali Ahmadvand Emory University Yang Liu Microsoft Research Ahmed Hassan Awadallah Microsoft Research Ming Zhong University of Illinois Milad Shokouhi Microsoft Research Abstract The recent increase in the volume of online meetings necessitates automated tools for orga- nizing the material, especially when an attendee has missed the discussion and needs assistance in quickly exploring it. In this work, we pro- pose a novel end-to-end framework for gener- ating 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 strat- egy by measuring how much the generated questions via questionnaire are answerable to ensure factual correctness and covers the source meeting for the depth of possible exploration. 1 Introduction In recent years, video conferencing technology has gained substantial improvements, and thus, online meetings have become easily accessible and more prominent. Primarily due to the pandemic and working from home, the need for video calling has grown significantly. Therefore, the high volume of online meetings necessitates automated tools for managing and organizing essential information for attendees. Especially when an attendee has missed an online meeting, it is critical to access the required information since quickly reading through the transcript is quite time-consuming. Providing meeting summaries is a promising di- rection (Wang and Cardie, 2013; Jacquenet et al., 2019; Zhao et al., 2019; Singhal et al., 2020). How- ever, recent studies show that 1) users’ needs do not fully align with current approaches to auto- matic text summarization (ter Hoeve et al., 2020, 2022) and 2) approaches designed for document summarization could not effectively apply to meet- ings transcripts (Murray et al., 2010; Mehdad et al., 2013; Li et al., 2019) due to the following potential reasons: (R1) Structure: standard documents are well structured compared to meeting transcripts; Figure 1: An example of exploring one of the meetings from the collection (Carletta et al., 2005) based on user preferences through an interactive questionnaire. (R2) Language: spoken language used in meetings is less regular than documents; and (R3) Multiple speakers: the speaker role is essential. Moreover, there is little meeting data publicly available that can be used for experimentation compared to regu- lar documents such as news or articles. In contrast with document summarization, when summarizing a meeting, different users tend different preferences on what content should be included in the summary. Therefore, there is an increasing calling for alterna- tive ways of summarizing, especially for meetings transcripts. Recently, Zhong et al. (2021) attempted to tackle this problem by proposing a query-based multi-domain meeting summary, where a user pro- vides a query in question form, e.g., ‘What was the discussion about the jog dial’s function when talk- ing about changes in the current design?’ to …

Content truncated to 500 words