Beyond Text Generation:

Supporting Writers with Continuous Automatic Text Summaries

UIST '22: Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology
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.
Is the alt-text updated?

Our UI (in the final version for study 2) with text editor (left) and a sidebar (right), which shows one card per paragraph. Typing is possible only in the editor. The cards’ content is controlled with the top buttons (original, central sentence, summary, keywords). These summaries are updated while typing. Editor and sidebar can be scrolled independently. Clicking a card scrolls to its paragraph in the editor and highlights it (in green for 1 second).

Demo:

BibTeX: 

@inproceedings{10.1145/3526113.3545672,
author = {Dang, Hai and Benharrak, Karim and Lehmann, Florian and Buschek, Daniel},
title = {Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summaries},
year = {2022},
isbn = {9781450393201},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3526113.3545672},
doi = {10.1145/3526113.3545672},
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.},
booktitle = {Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology},
articleno = {98},
numpages = {13},
keywords = {Natural Language Processing, Text documents, reverse outlining, semantic zoom, text summarization},
location = {Bend, OR, USA},
series = {UIST '22}
}