- NLP - dsv.su.se

Invited speech: June 3, at 14-15.00 Open access to research data and automatic pseudonymization. Two years with Mormor Karl project.

by Hercules Dalianis

Dear NLP group Invited speech by professor Elena Volodina, professor at Språkbanken Text; Dpt. Swedish, Multilingualism, Language Technology, University of Gothenburg. Time: Tuesday, June 3, at 14-15.00 Place: Lilla Hörsalen Title: Open access to research data and automatic pseudonymization. Two years with Mormor Karl project. Abstract: This talk will be devoted to the challenges of working with data that contains personal information. I will describe a set of experiments with automatic pseudonymization that we have performed within Mormor Karl project<https://mormor-karl.github.io/>. Among others, experiments with detection and labeling of personal categories using BERT models (Szawerna et al. 2024, 2025), attempts att using LLMs to "fill in the blanks" when substituting personal information with pseudonyms (yet unpublished) and a study on whether pseudonyms can provoke biased automated classifications (Muñoz Sánchez et al. 2024). The choice of models for our experiments is currently dictated by the sensitive nature of our data. To extend the choice from open source to proprietary models, we are currently collecting a "pseudo-corpus" with fictitious personal information that we will be able to share freely for future research (you are welcome to contribute to the pseudo-corpus collection<https://forms.gle/t4ynDJwqfmFXYitPA> as well). Finally, in this talk I will name several strategies to unify the research on automatic pseudonymization, and outline further challenges, needs for standardization and a proposal of a shared task. * Maria Irena Szawerna, Simon Dobnik, Ricardo Muñoz Sánchez, and Elena Volodina. 2025. The Devil’s in the Details: the Detailedness of Classes Influences Personal Information Detection and Labeling<https://hdl.handle.net/10062/107263>. In Proceedings of the The Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025). * Maria Irena Szawerna, Simon Dobnik, Ricardo Muñoz Sánchez, Therese Lindström Tiedemann and Elena Volodina. 2024. Detecting Personal Identifiable Information in Swedish Learner Essays<https://aclanthology.org/2024.caldpseudo-1.7/>. In Proceedings of the the EACL workshop Computational Approaches to Language Data Pseudonymization (CALD-pseudo-2024). EACL, Malta, 2024. Association for Language Technology. * Ricardo Muñoz Sánchez, Simon Dobnik, Maria Irena Szawerna, Therese Lindström Tiedemann and Elena Volodina. 2024. Did the Names I Used within My Essay Affect My Score? Diagnosing Name Biases in Automated Essay Scoring<https://aclanthology.org/2024.caldpseudo-1.10/>. In Proceedings of the the EACL workshop Computational Approaches to Language Data Pseudonymization (CALD-pseudo-2024). EACL, Malta, 2024. Association for Language Technology. Warm welcome Hercules _________________________________________________________________________ Dr. Hercules Dalianis, Professor Department of Computer and Systems Sciences ph: +46 8 16 16 16 DSV/Stockholm University mobile ph: +46 70 568 13 59 P.O. Box 7003, 164 07 Kista email: hercules(a)dsv.su.se Stockholm, Sweden www: http://www.dsv.su.se/hercules/ _________________________________________________________________________

4 days, 23 hours

1
0
0 0

Tandem Health creates patient records for the doctor

by Hercules Dalianis

Very interesting application in health care by Tandel Health Svenska https://www.tandemhealth.ai/sv/press English https://www.tandemhealth.ai/press Best Hercules _________________________________________________________________________

1 week, 6 days

1
0
0 0

Report from Nodalida 2025 by Martin Hansson and Thomas Vakili

by Hercules Dalianis

Dear all I am attaching the conference report from Nodalida 2025 by Martin Hansson and Thomas Vakili. I would like to add that they presented their paper with the title "SweClinEval: A Benchmark for Swedish Clinical Natural Language Processing” written jointly with Aron Henriksson, as well at the conference. Best Hercules _________________________________________________________________________ Dr. Hercules Dalianis, Professor Department of Computer and Systems Sciences ph: +46 8 16 16 16 DSV/Stockholm University mobile ph: +46 70 568 13 59 P.O. Box 7003, 164 07 Kista email: hercules(a)dsv.su.se Stockholm, Sweden www: http://www.dsv.su.se/hercules/ _________________________________________________________________________

1 month, 2 weeks

1
0
0 0

NLP group meeting, March 19 at 12-13.00 in M20

by Hercules Dalianis

Dear all Here is a call for the upcoming NLP group meeting next week (Wednesday March 19, at 12-13 in M20). The agenda for the meeting is: 1. Round-of-table news (accepted papers, conference trips, application etc.) 2. Presentation by Korbinian Randl of his article written jointly with Aron et al. and presented at the International Conference on Discovery Science, "Evaluating the Reliability of Self-explanations in Large Language Models”, https://link.springer.com/chapter/10.1007/978-3-031-78977-9_3 3. Any other business Bring your lunch and we will arrange some “fika” for the coffee. Warm welcome Hercules & Aron _________________________________________________________________________ Dr. Hercules Dalianis, Professor Department of Computer and Systems Sciences ph: +46 8 16 16 16 DSV/Stockholm University mobile ph: +46 70 568 13 59 P.O. Box 7003, 164 07 Kista email: hercules(a)dsv.su.se Stockholm, Sweden www: http://www.dsv.su.se/hercules/ _________________________________________________________________________ Here is a call of the coming NLP group meeting in two weeks (Wednesday Feb 19, at 12-13 in M10) The agenda for the NLP meeting is: 1. Round-of-table news (accepted papers, conference trips, application etc.) 2. Presentation by Thomas Vakili and Martin Hansson of their accepted paper jointly with Aron to Nodalida 2025 in March in Tartu, Estonia with title: SweClinEval: A Benchmark for Swedish Clinical Natural Language Processing 3. Any other business Bring your lunch and we will arrange some “fika” for the coffee. Best Hercules & Aron 5 feb. 2025 kl. 12:29 skrev Hercules Dalianis <hercules(a)dsv.su.se>: Dear all Here is a call of the coming NLP group meeting in two weeks (Wednesday Feb 19, at 12-13 in M10) The agenda for the NLP meeting is: 1. Round-of-table news (accepted papers, conference trips, application etc.) 2. Presentation by Thomas Vakili and Martin Hansson of their accepted paper jointly with Aron to Nodalida 2025 in March in Tartu, Estonia with title: SweClinEval: A Benchmark for Swedish Clinical Natural Language Processing 3. Any other business Bring your lunch and we will arrange some “fika” for the coffee. Best Hercules & Aron _________________________________________________________________________ Dr. Hercules Dalianis, Professor Department of Computer and Systems Sciences ph: +46 8 16 16 16 DSV/Stockholm University mobile ph: +46 70 568 13 59 P.O. Box 7003, 164 07 Kista email: hercules(a)dsv.su.se Stockholm, Sweden www: http://www.dsv.su.se/hercules/ _________________________________________________________________________ 6 dec. 2024 kl. 09:23 skrev Aron Henriksson <aronhen(a)dsv.su.se>: Hi all, Here is a reminder of the NLP group meeting next week (Thursday 12-13 in M20), with an updated agenda: The agenda for the meeting is: 1. Round-of-table news (accepted papers, conference trips etc.) 2. Presentation by Yongchao Wu of his ECML-PKDD paper: “Selecting from Multiple Strategies Improves the Foreseeable Reasoning of Tool-Augmented Large Language Models” 3. Presentation by Shaghayegh Abedi, master student at Politecnico di Torino (Polito), Italy: “Using GenAI & Decision Model and Notation (DMN) to support giving feedback to students” (a thesis to be supervised by Amin) We have also planned for an afterwork the same evening for anyone who is interested! Best, Aron —— Aron Henriksson Associate Professor (Docent) Department of Computer and Systems Sciences (DSV) Stockholm University P.O. Box 1073, SE-164 25 Kista, Sweden Visiting address: Borgarfjordsgatan 12, Kista Phone: +46-8-164985 On 21 Nov 2024, at 13:32, Aron Henriksson <aronhen(a)dsv.su.se> wrote: Hi all, It’s time for another NLP group meeting! I have booked M20 on Dec 12 from 12-13. The agenda for the meeting is: 1. Round-of-table news (accepted papers, conference trips etc.) 2. Presentation by Yongchao Wu of his ECML-PKDD paper: “Selecting from Multiple Strategies Improves the Foreseeable Reasoning of Tool-Augmented Large Language Models” 3. Any other issues Feel free to bring your lunch to the meeting and I will arrange some “fika” for the coffee. We also plan to have an afterwork the same evening, from around 17.30, feel free to join us! Let me know if you any suggestions for what to do & where to go. Best, Aron —— Aron Henriksson Associate Professor (Docent) Department of Computer and Systems Sciences (DSV) Stockholm University P.O. Box 1073, SE-164 25 Kista, Sweden Visiting address: Borgarfjordsgatan 12, Kista Phone: +46-8-164985 _______________________________________________ NLP mailing list -- nlp(a)dsv.su.se To unsubscribe send an email to nlp-leave(a)dsv.su.se

1 month, 4 weeks

1
0
0 0

Fwd: Doktorandfestivalen @ SU

by Thomas Vakili

Hi all, I received this invitation and thought I would share it with you, in particular with the rest of the PhD students! I attended last year and had a really fruitful afternoon. It was also a good opportunity to share what I'm working on at DSV and learn what the linguists are doing. Some of the PhD students are doing research in NLP, others are doing NLP-adjacent work (and of course some are doing more purely linguistic research). Best regards, Thomas Vakili *____________________________________* *Thomas Vakili* PhD student Department of Computer and Systems Sciences *Stockholm University* Borgarfjordsgatan 12, Kista Tel: +46 8-16 16 59 https://vakili.science *____________________________________* -------- Forwarded Message -------- Subject: Doktorandfestivalen @ SU Date: Mon, 17 Feb 2025 10:43:05 +0100 From: Crina Madalina Tudor <crina.tudor(a)ling.su.se> To: Thomas Vakili <thomas.vakili(a)dsv.su.se> Hi Thomas, I hope this email finds you well! On behalf of the PhD council at the Department of Linguistics, I would like to extend an invitation to the PhD students from your department to attend our PhD student festival (DokFest). Kindly forward this invite to any and all students who could be interested in this initiative. The PhD students at the Department of Linguistics warmly invite you to DokFest, where PhD students within linguistics and language-related cognitive sciences present their ongoing work. We have planned out a fun day that starts off with presentations and ends with dinner and festivities. Participation is free of charge. PhD students from other departments/universities are more than welcome to attend, and are invited to optionally present a poster with their own research during the event. Registration will be open until *Friday, March 21th*, at 23:59, and is available through the following link: https://form.jotform.com/250411009494349 <https://form.jotform.com/250411009494349> . Presenters need to submit an abstract upon attending, as we’re putting together a book of abstracts. Abstracts should be no more than 300 words and, if references are needed, please use APA formatting. If you are planning to present, please send in your abstract to christoffer.forbes.schieche(a)ling.su.se <mailto:christoffer.forbes.schieche@ling.su.se> by *April 4th*, at 23:59. *DOKFEST* *Date*: Friday, April 11th *Place*: Hörsal 11, Södra huset F, 3rd floor Preliminary schedule: 13:00 – 17:00 PhD project presentations & poster sessions 17:00 – 18:00 Dinner (for presenters and department faculty) 18:00 – Mingle If you have any questions, please reach out to doktorand(a)ling.su.se <mailto:doktorand@ling.su.se> . Kind regards, Crina *____________________________________* *Crina Tudor* PhD student *Stockholm University* SE-106 91 Stockholm, Sweden Visiting address: Rum C246 Universitetsvägen 10 C, plan 2-3 Email: crina.tudor(a)ling.su.se https://www.su.se/institutionen-for-lingvistik/ <https://www.su.se/institutionen-for-lingvistik/> How personal data is handled at Stockholm University <https://www.su.se/english/about-this-website-1.517563?open-collapse-boxes=c…> *____________________________________*

2 months, 2 weeks

1
0
0 0

NLP group meeting, Dec 12 at 12-13.00 in M20 + AW

by Aron Henriksson

Hi all, It’s time for another NLP group meeting! I have booked M20 on Dec 12 from 12-13. The agenda for the meeting is: 1. Round-of-table news (accepted papers, conference trips etc.) 2. Presentation by Yongchao Wu of his ECML-PKDD paper: “Selecting from Multiple Strategies Improves the Foreseeable Reasoning of Tool-Augmented Large Language Models” 3. Any other issues Feel free to bring your lunch to the meeting and I will arrange some “fika” for the coffee. We also plan to have an afterwork the same evening, from around 17.30, feel free to join us! Let me know if you any suggestions for what to do & where to go. Best, Aron —— Aron Henriksson Associate Professor (Docent) Department of Computer and Systems Sciences (DSV) Stockholm University P.O. Box 1073, SE-164 25 Kista, Sweden Visiting address: Borgarfjordsgatan 12, Kista Phone: +46-8-164985

3 months

2
3
0 0

Yongchao Wu's dissertation defence on Dec 16

by Aron Henriksson

Hi all, Welcome to Yongchao's dissertation defence on Dec 16! The defence starts at 9 am in L30. He will defend his thesis: "Exploring the Educational Utility of Pretrained Language Models”. Prof. Filip Ginter from the University of Turku will be the opponent. See here for more information: https://internt.dsv.su.se/sv/node/1791. Here is a link to the thesis: https://www.diva-portal.org/smash/record.jsf?pid=diva2:1909361. Hope to see many NLPers there! Best, Aron —— Aron Henriksson Associate Professor (Docent) Department of Computer and Systems Sciences (DSV) Stockholm University P.O. Box 1073, SE-164 25 Kista, Sweden Visiting address: Borgarfjordsgatan 12, Kista Phone: +46-8-164985

5 months

1
0
0 0

Yongchao's nailing on Nov 21

by Aron Henriksson

Hi all, Welcome to join us for Yongchao’s nailing next Thursday (Nov 21) ahead of his dissertation defence on Dec 16! We will gather in the lobby on the 3rd floor (entrance E) at 11:30. Best, Aron —— Aron Henriksson Associate Professor (Docent) Department of Computer and Systems Sciences (DSV) Stockholm University P.O. Box 1073, SE-164 25 Kista, Sweden Visiting address: Borgarfjordsgatan 12, Kista Phone: +46-8-164985

5 months, 2 weeks

1
1
0 0

Kodknäckare Forskning och Framsteg no 9, 2024 - Beata Megyesi

by Hercules Dalianis

Dear A nice article about code breaking of historical texts by our colleague professor Beata Megyesi at department of Linguistics SU in Forskning och Framsteg no 9, 2024. It is in Swedish for those who knows to read it. Attached, Otherwise description of her work in English https://www.su.se/english/news/the-computational-linguist-who-cracks-histor… Beate's code breaking together with other colleagues were mentioned in several newspapers and broadcasts in the world see here, https://www.su.se/polopoly_fs/1.688306.1699263703!/menu/standard/file/get-C… Best Hercules _________________________________________________________________________ Dr. Hercules Dalianis, Professor Department of Computer and Systems Sciences ph: +46 8 16 16 16 DSV/Stockholm University mobile ph: +46 70 568 13 59 P.O. Box 1073, 164 25 Kista email: hercules(a)dsv.su.se Stockholm, Sweden www: http://www.dsv.su.se/hercules/ _________________________________________________________________________

6 months

1
0
0 0

NLP group meeting, Oct 29 at 12-13.00 in M20

by Aron Henriksson

Hi all, It’s time for another NLP group meeting! I have booked M20 on Oct 29 from 12-13. The agenda for the meeting is: 1. Round-of-table news (accepted papers, conference trips etc.) 2. Presentation by Thomas Vakili on "Private NLP with Synthetic Training Data” 3. Any other issues Feel free to bring your lunch to the meeting and I will arrange some “fika” for the coffee. Best, Aron —— Aron Henriksson Associate Professor (Docent) Department of Computer and Systems Sciences (DSV) Stockholm University P.O. Box 1073, SE-164 25 Kista, Sweden Visiting address: Borgarfjordsgatan 12, Kista Phone: +46-8-164985

6 months, 1 week

2
1
0 0

2025

2024

NLP ----- 2025 ----- May 2025 April 2025 March 2025 February 2025 January 2025 ----- 2024 ----- December 2024 November 2024 October 2024 September 2024 August 2024 July 2024 June 2024

NLP