1st call for Papers WR-AI-CogS1 Writing Aids at the Crossroads of AI, Cognitive Science and NLP
Co-located with COLING 2025 (Abu Dhabi, https://coling2025.org/)
Workshop website: https://sites.google.com/view/wraicogs1
Paper submission deadline: 25 November, 2024
link for paper submission: https://softconf.com/coling2025/AAC-AI25/
Keynote speaker:
Cerstin Mahlow, Professor of Digital Linguistics and Writing Research, ZHAW School of Applied
Linguistics, Winterthur, Switzerland (https://www.zhaw.ch/en/about-us/person/maho/)
* Motivation
Writing is one of the four cornerstones of communication. By leaving a trace, it allows us to reach
many people, to transcend space and time, and to spare us the trouble of memorization. Obviously,
writing is important. What is less obvious though is the process, i.e., the precise steps to carry out to
get from a vague idea to concrete, well-polished prose. Producing readable, well-written text requires
many skills, deep and broad knowledge of various sorts —(topic, language, audience; metaknowledge:
how to use best the information at hand?)— a lot of practice and high-quality feedback.
No one can learn all this overnight, and the quantity and diversity of knowledge to interiorize may
explain why writing is so difficult and why it takes so much time to gain control over the whole
process and become an expert writer. Alas, knowledge is not all. Writing is also a time and energyconsuming
activity.
Since writing is difficult, and since there are nowadays computer programs able to do the job one
may wonder
(a) whether we should not leave the job to the machine, or
(b) whether we could not use them to help people to write or to acquire the skill of writing.
Indeed, there are situations where it makes sense to rely on machines (routine work, business letters),
but there are also quite a few others where one wouldn’t recommend this strategy at all (education).
This being said, one may find a middle ground, a situation where humans and machines work together,
each one contributing what they are best at. It remains to be seen where in the process machines can
help and where it is better to leave the control to humans. Hence, the main question is not ‘shall we
use GPT to produce texts,’ but rather ‘how and when (what level)’ to use LLMs (or other techniques)
to help people to produce written text.
In sum, our main goal is not to substitute machines for people, having them do the job in people’s
place, but rather have machines assist people. That is, we want to help people to learn, to speed up
the process of writing, to gain better control, and to reduce the cognitive load. Our motivation is
largely educational. Obviously, we are not the first ones to pursue this goal.
Still, even if many workshops have been devoted to the building of educational software, the
development of intelligent writing assistants, or the evaluation of written text, the submitted papers
were generally only concerned with the formal aspects, that is, the lower end of writing: grammatical
error detection, spotting of spelling mistakes, etc. Yet good writing (text composition) requires way
more than just the production of well-formed sentences.
Our mission or ambition is to go beyond that. We are interested in the full spectrum of writing. Hence,
we welcome not only papers devoted to the lower aspects of writing (grammar, spelling, …), but also
to the higher levels, the ones preceding writing: thinking, reasoning, planning (idea generation,
outline planning, etc.).
Unless mistaken, this is the first workshop to consider
(a) the entire spectrum of writing hence also the higher levels of composition: planning (ideation,
organization), drafting/expression; editing; revision,
(b) to integrate right from the start humans into the loop of the development cycle, and
(c) to consider support and feedback at any moment —before, during, and after writing— rather than
only at the very end.
* Topics
We solicit contributions on all topics related to writing aids, including but not limited to the following:
Topic 1: The human perspective
– How to include humans into the development cycle?
– What do people typically know? What are their problems and needs?
– What components should an authoring eco-system have?
– What kind of shared task would be meaningful while being technically feasable?
Topic 2: The engineering side
– Where in the process could we use methods developed in AI (LLMs) or computational linguistics?
– What should an authoring ecosystem look like? (What could be automated? What is best left for
interactive processing?)
– How to help people to organize their ideas into a coherent whole?
– How to detect possible topics within our data?
– How to identify typical subtopics of a given topic?
– How to enhance text analysis by using tools like Sketch Engine?
Topic 3: The cognitive scientific point of view (psycholinguistics, neuroscience)
– How and at what level can engineers use the insights gained in psycholinguistics and neuroscience ?
Topic 4: General issues
Checking of facts, relevance, cohesion, coherence, style, fluency, grammar, word choice, spelling.
* Submission Instructions
Please submit your papers via the START/SoftConf submission portal
(https://softconf.com/coling2025/AAC-AI25/), following the COLING 2025 templates.. The
submitted versions have to be anonymous and should not exceed 8 pages for long papers and 4 pages
for short papers. The references don’t count for the page limit, and they can be up to 4 pages long.
Supplementary material, and appendices are also allowed.
* Workshop Organizers
– Michael Zock (CNRS, LIS, Aix-Marseille University, Marseille, France)
– Kentaro Inui (Mohamed bin Zayed University of Artificial Intelligence, UAE; Tohoku University,
Japan)
– Zheng Yuan (King’s College, London and University of Cambridge, UK)
* Program Committee
1. Barbu Mititelu, V. (Research Institute for Artificial Intelligence, RACAI, Bucharest, Romania)
2. Biemann, C. (Language Technology group, Universität Hamburg, Germany)
3. Bryant, Christopher (Writer Inc., USA & University of Cambridge, UK)
4. Bunt, Harry (Tilburg University, Department of Cognitive Science and Artificial Intelligence)
5. Church, Ken (Northeastern University, USA)
6. Cristea, Dan (University of Iasi, Iasi, Romania
7. Coyne, Steven (Tohoku University, Sendai, Japan)
8. Dale, Robert (Language Technology Group, Church Point, NSW, Australia)
9. Delmonte, Rodolfo (Department of Computer Science, Università Ca’ Foscari, Italy)
10. Evert, Stephani (Computational Corpus Linguistics at Friedrich-Alexander-Universität Erlangen-
Nürnberg, Germany)
11. Ferret, Olivier (CEA LIST, France)
12. Fontenelle, Thierry (European Investment Bank, Luxembourg)
13. François, Thomas (CENTAL, Université catholique de Louvain, Belgium)
14. Gadeau, Gabriella ((Department of Computer Science and Technology, University of Cambridge,
UK)
15. Galván, Diana (University of Cambridge)
16. Guerraoui, Camélia (Tohoku University, Sendai, Japan)
17. Hernandez, Nicolas (University of Nantes, France)
18. Hovy, Edward (University of Melbourne, Australia, and Carnegie Mellon, USA)
19. Iacobacci, Ignacio (London’s Speech and Semantics Lab, UK)
20. Ishii, Yutaka (Chiba University)
21. Ito, Takumi (Langsmith/Tohoku University )
22. Lafourcade, Mathieu (Université de Montpellier, France)
23. Langlais, Felipe. (DIRO/RALI, University of Montreal, Canada)
24. Mahlow, Cerstin (ZHAW School of Applied Linguistics, Winterthur, Switzerland)
25. Matsubayashi, Yuichiro (Tohoku University)
26. Pease, Adam (Parallax Research, Beavercreek, OH, USA)
27. Pirrelli, Vito (Institute of Computational Linguistics, University of Pisa)
28. Raganato, Alessandro (DISCO, University of Milano-Bicocca, Italy)
29. Redeker, Gisela (University of Groningen, The Netherlands)
30. Reed, Chris (University of Dundee, Scotland)
31. Reiter, Ehud (University of Aberdeen, Scotland)
32. Rosso, Paolo (Universitat Politècnica de València, Spain)
33. Saggion, Horacio (Universitat Pompeu Fabra, Spain)
34. Schwab, Didier (GETALP-LIG, Grenoble, France)
35. Strapparava, Carlo (Fondazione Bruno Kessler, Trento, Italy)
36. Tesfaye, Debela (University of Dundee, Scotland)
37. Wanner, Leo (Universitat Pompeu Fabra, Spain)
38. Winniwarter, W. (CSLEARN – Educational Technologies, Vienna, Austria)
39. Zheng, Yuan (King’s College, London)