EMNLP 2021system demonstrations12 citations

Summary Explorer: Visualizing the State of the Art in Text Summarization

Shahbaz Syed, Tariq Yousef, Khalid Al Khatib, Stefan Jänicke, Martin Potthast

Abstract

This paper introduces Summary Explorer, a new tool to support the manual inspection of text summarization systems by compiling the outputs of 55 state-of-the-art single document summarization approaches on three benchmark datasets, and visually exploring them during a qualitative assessment. The underlying design of the tool considers three well-known summary quality criteria (coverage, faithfulness, and position bias), encapsulated in a guided assessment based on tailored visualizations. The tool complements existing approaches for locally debugging summarization models and improves upon them. The tool is available at https://tldr.webis.de/

BibTeX
@inproceedings{syed-etal-2021-summary,
    title = "Summary Explorer: Visualizing the State of the Art in Text Summarization",
    author = {Syed, Shahbaz  and
      Yousef, Tariq  and
      Al Khatib, Khalid  and
      J{\"a}nicke, Stefan  and
      Potthast, Martin},
    editor = "Adel, Heike  and
      Shi, Shuming",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.emnlp-demo.22/",
    doi = "10.18653/v1/2021.emnlp-demo.22",
    pages = "185--194"
}
Summary Explorer: Visualizing the State of the Art in Text Summarization · EMNLP 2021