ConceptEVA: Concept-Based Interactive Exploration and Customization of Document Summaries

要旨

With the most advanced natural language processing and artificial intelligence approaches, effective summarization of long and multi-topic documents---such as academic papers---for readers from different domains still remains a challenge. To address this, we introduce ConceptEVA, a mixed-initiative approach to generate, evaluate, and customize summaries for long and multi-topic documents. ConceptEVA incorporates a custom multi-task longformer encoder decoder to summarize longer documents. Interactive visualizations of document concepts as a network reflecting both semantic relatedness and co-occurrence help users focus on concepts of interest. The user can select these concepts and automatically update the summary to emphasize them. We present two iterations of ConceptEVA evaluated through an expert review and a within-subjects study. We find that participants' satisfaction with customized summaries through ConceptEVA is higher than their own manually-generated summary, while incorporating critique into the summaries proved challenging. Based on our findings, we make recommendations for designing summarization systems incorporating mixed-initiative interactions.

著者
Xiaoyu Zhang
University of California, Davis, Davis, California, United States
Jianping Li
University of California, Davis, Davis, California, United States
Po-Wei Chi
None, pwchi@ucdavis.edu, California, United States
Senthil Chandrasegaran
Delft University of Technology, Delft, Netherlands
Kwan-Liu Ma
University of California at Davis, Davis, California, United States
論文URL

https://doi.org/10.1145/3544548.3581260

動画

会議: CHI 2023

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2023.acm.org/)

セッション: Discovery Track Thursday

Hall A
3 件の発表
2023-04-27 18:00:00
2023-04-27 19:30:00