CoChat

Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summaries

Open access
Dang, Hai, Benharrak, Karim, Lehmann, Florian, Buschek, Daniel · 2022 · Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology
Cited by 84

The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.

Abstract

We propose a text editor to help users plan, structure and reflect on their writing process. It provides continuously updated paragraph-wise summaries as margin annotations, using automatic text summarization. Summary levels range from full text, to selected (central) sentences, down to a collection of keywords. To understand how users interact with this system during writing, we conducted two user studies (N=4 and N=8) in which people wrote analytic essays about a given topic and article. As a key finding, the summaries gave users an external perspective on their writing and helped them to revise the content and scope of their drafted paragraphs. People further used the tool to quickly gain an overview of the text and developed strategies to integrate insights from the automated summaries. More broadly, this work explores and highlights the value of designing AI tools for writers, with Natural Language Processing (NLP) capabilities that go beyond direct text generation and correction.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3526113.3545672

Cites

16 of 16 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 36

  1. 10.1145/2858036.2858407 · DOI
  2. Kenneth C Arnold , April M Volzer , and Noah G Madrid . 2021 . Generative Models can Help Writers without Writing for Them . 2nd Workshop on Human-AI Co-Creation with Generative Models - HAI-GEN 2021 (2021), 8. Kenneth C Arnold, April M Volzer, and Noah G Madrid. 2021. Generative Models can Help Writers without Writing for Them. 2nd Workshop on Human-AI Co-Creation with Generative Models - HAI-GEN 2021 (2021), 8.
  3. 10.1145/3468505 · DOI · Paper page
  4. 10.1145/3411764.3445372 · DOI · Paper page
  5. Hakan Ceylan and Rada Mihalcea . 2009. The Decomposition of Human-Written Book Summaries . In Computational Linguistics and Intelligent Text Processing, Alexander Gelbukh (Ed.). Vol. 5449. Springer Berlin Heidelberg , Berlin, Heidelberg, 582–593. https://doi.org/10.1007/978-3-642-00382-0_47 Series Title : Lecture Notes in Computer Science. 10.1007/978-3-642-00382-0_47 Hakan Ceylan and Rada Mihalcea. 2009. The Decomposition of Human-Written Book Summaries. In Computational Linguistics and Intelligent Text Processing, Alexander Gelbukh (Ed.). Vol. 5449. Springer Berlin Heidelberg, Berlin, Heidelberg, 582–593. https://doi.org/10.1007/978-3-642-00382-0_47 Series Title: Lecture Notes in Computer Science. · doi:10.1007/978-3-642-00382-0_47
  6. Juliet M Corbin . 1990. Basics of qualitative research: Grounded theory procedures and techniques . Sage . Juliet M Corbin. 1990. Basics of qualitative research: Grounded theory procedures and techniques. Sage.
  7. 10.1093/elt/54.3.235 · DOI · Paper page
  8. 10.2307/356600 · doi:10.2307/356600 · Paper page
  9. 10.18653/v1/P17-4008 · DOI
  10. Han L. Han , Miguel A. Renom , Wendy E. Mackay , and Michel Beaudouin-Lafon . 2020 . Textlets: Supporting Constraints and Consistency in Text Documents . Association for Computing Machinery , New York, NY, USA , 1–13. https://doi.org/10.1145/3313831.3376804 10.1145/3313831.3376804 Han L. Han, Miguel A. Renom, Wendy E. Mackay, and Michel Beaudouin-Lafon. 2020. Textlets: Supporting Constraints and Consistency in Text Documents. Association for Computing Machinery, New York, NY, USA, 1–13. https://doi.org/10.1145/3313831.3376804 · DOI
  11. 10.1145/3377325.3377485 · DOI
  12. 10.1145/2939672.2939801 · DOI · Paper page
  13. 10.1109/TPC.2012.2207838 · DOI
  14. Wojciech Kryscinski , Nitish Shirish Keskar , Bryan McCann , Caiming Xiong , and Richard Socher . 2019. Neural Text Summarization: A Critical Evaluation . In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) . Association for Computational Linguistics , Hong Kong , China, 540–551. https://doi.org/10. 1865 3/v1/D19-1051 10.18653/v1 Wojciech Kryscinski, Nitish Shirish Keskar, Bryan McCann, Caiming Xiong, and Richard Socher. 2019. Neural Text Summarization: A Critical Evaluation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, 540–551. https://doi.org/10.18653/v1/D19-1051 · doi:10.18653/v1
  15. 10.1016/j.ipl.2017.10.007 · doi:10.1016/j.ipl.2017.10.007
  16. Karen Sheriff LeVan and Marissa E King . 2017 . Self-Annotation as a Course Practice . Teaching English in the Two Year College 44 , 3 (2017), 289 . Karen Sheriff LeVan and Marissa E King. 2017. Self-Annotation as a Course Practice. Teaching English in the Two Year College 44, 3 (2017), 289. · doi:10.58680/tetyc201729004
  17. Daniel Li , Thomas Chen , Albert Tung , and Lydia B Chilton . 2021 . Hierarchical Summarization for Longform Spoken Dialog. In The 34th Annual ACM Symposium on User Interface Software and Technology ( Virtual Event, USA) (UIST ’21). Association for Computing Machinery, New York, NY, USA, 582–597. https://doi.org/10.1145/3472749.3474771 10.1145/3472749.3474771 Daniel Li, Thomas Chen, Albert Tung, and Lydia B Chilton. 2021. Hierarchical Summarization for Longform Spoken Dialog. In The 34th Annual ACM Symposium on User Interface Software and Technology (Virtual Event, USA) (UIST ’21). Association for Computing Machinery, New York, NY, USA, 582–597. https://doi.org/10.1145/3472749.3474771 · DOI
  18. Yang Li , Sayan Sarcar , Sunjun Kim , and Xiangshi Ren . 2020 . Swap: A Replacement-Based Text Revision Technique for Mobile Devices . Association for Computing Machinery , New York, NY, USA , 1–12. https://doi.org/10.1145/3313831.3376217 10.1145/3313831.3376217 Yang Li, Sayan Sarcar, Sunjun Kim, and Xiangshi Ren. 2020. Swap: A Replacement-Based Text Revision Technique for Mobile Devices. Association for Computing Machinery, New York, NY, USA, 1–12. https://doi.org/10.1145/3313831.3376217 · DOI
  19. 10.1109/TCOM.1982.1095380 · DOI
  20. Kristin Messuri . 2016 . Revision Strategies . The Southwest Respiratory and Critical Care Chronicles 4 , 14 (April 2016), 46–48. https://pulmonarychronicles.com/index.php/pulmonarychronicles/article/view/263 Number: 14. Kristin Messuri. 2016. Revision Strategies. The Southwest Respiratory and Critical Care Chronicles 4, 14 (April 2016), 46–48. https://pulmonarychronicles.com/index.php/pulmonarychronicles/article/view/263 Number: 14.
  21. 10.12746/swrccc.v4i15.290 · doi:10.12746/swrccc.v4i15.290
  22. Rada Mihalcea and Paul Tarau . 2004 . Textrank: Bringing order into text . In Proceedings of the 2004 conference on empirical methods in natural language processing. 404–411 . Rada Mihalcea and Paul Tarau. 2004. Textrank: Bringing order into text. In Proceedings of the 2004 conference on empirical methods in natural language processing. 404–411.
  23. Michael J. Muller and Sandra Kogan . 2012 . Grounded Theory Method in Human-Computer Interaction and Computer-Supported Cooperative Work. In The Human–Computer Interaction Handbook (3 ed.). CRC Press . Num Pages: 21. Michael J. Muller and Sandra Kogan. 2012. Grounded Theory Method in Human-Computer Interaction and Computer-Supported Cooperative Work. In The Human–Computer Interaction Handbook (3 ed.). CRC Press. Num Pages: 21.
  24. 10.1162/089120102762671927 · DOI · Paper page
  25. Hariharan Subramonyam , Colleen Seifert , Priti Shah , and Eytan Adar . 2020. TexSketch: Active Diagramming through Pen-and-Ink Annotations . Association for Computing Machinery , New York, NY, USA , 1–13. https://doi.org/10.1145/3313831.3376155 10.1145/3313831.3376155 Hariharan Subramonyam, Colleen Seifert, Priti Shah, and Eytan Adar. 2020. TexSketch: Active Diagramming through Pen-and-Ink Annotations. Association for Computing Machinery, New York, NY, USA, 1–13. https://doi.org/10.1145/3313831.3376155 · DOI · Paper page
  26. 10.1007/978-3-540-89454-4_5 · DOI
  27. Pradyumna Tambwekar Murtaza Dhuliawala Lara J. Martin Animesh Mehta Brent Harrison and Mark O. Riedl. 2018. Controllable Neural Story Plot Generation via Reinforcement Learning. arxiv:1809.10736 [cs.CL] Pradyumna Tambwekar Murtaza Dhuliawala Lara J. Martin Animesh Mehta Brent Harrison and Mark O. Riedl. 2018. Controllable Neural Story Plot Generation via Reinforcement Learning. arxiv:1809.10736 [cs.CL] · DOI
  28. 10.1145/3343413.3377971 · DOI · Paper page
  29. L. Danielle Tully . 2019 . Reverse Outlines: Fueling Revision & Preparing for Writing Conferences . The Second Draft 32 , 2 (2019), 6 . https://ssrn.com/abstract=3465807 L. Danielle Tully. 2019. Reverse Outlines: Fueling Revision & Preparing for Writing Conferences. The Second Draft 32, 2 (2019), 6. https://ssrn.com/abstract=3465807
  30. 10.1145/2851581.2856472 · DOI
  31. 10.1145/3027063.3027066 · DOI
  32. 10.1145/3472749.3474765 · DOI
  33. Harriet Salatas Waters and Wolfgang Schneider. 2009. Metacognition Strategy Use and Instruction. Guilford Press. Harriet Salatas Waters and Wolfgang Schneider. 2009. Metacognition Strategy Use and Instruction. Guilford Press.
  34. Daijin Yang , Yanpeng Zhou , Zhiyuan Zhang , and Toby Jia-Jun Li . 2022 . AI as an Active Writer: Interaction strategies with generated text in human-AI collaborative fiction writing . In IUI 2022 Workshop on Human-AI Co-Creation with Generative Models (HAI-GEN 2022). 10. Daijin Yang, Yanpeng Zhou, Zhiyuan Zhang, and Toby Jia-Jun Li. 2022. AI as an Active Writer: Interaction strategies with generated text in human-AI collaborative fiction writing. In IUI 2022 Workshop on Human-AI Co-Creation with Generative Models (HAI-GEN 2022). 10.
  35. Demet Yaylı . 2012 . Tracing the benefits of self annotation in genre-based writing . The Journal of Language Learning and Teaching 2 , 1 (2012), 45 – 58 . Demet Yaylı. 2012. Tracing the benefits of self annotation in genre-based writing. The Journal of Language Learning and Teaching 2, 1 (2012), 45–58.
  36. 10.1145/3332165.3347924 · DOI · Paper page

Cited by

See all 84

Metadata

Authors
Dang, H., Benharrak, K., Lehmann, F., & Buschek, D.
Venue
Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology
Publisher
ACM
Published
2022-10-28
Pages
1-13
OpenAlex
W4292760860
Cited by
84
References
16
FWCI
15.44
Type
conference paper
Language
en
Open access
green
Funders
Bavarian State Ministry of Science and the Arts

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.