Emiel van Miltenburg
@evanmiltenburg.bsky.social
Assistant professor in computational linguistics/nlp. Interested in research methodology, ethics, multimodality, and accessibility.
Here's the list of accepted papers for #INLG2026: 2026.inlgmeeting.org/accepted-pap...
Much to see at the conference, but as always this will be a single-track program. I love this set-up, as it creates common ground for attendees to discuss what they've seen.
Registration is open now!
#NLP #AI
Much to see at the conference, but as always this will be a single-track program. I love this set-up, as it creates common ground for attendees to discuss what they've seen.
Registration is open now!
#NLP #AI
INLG2026
The 19th International Natural Language Generation Conference is scheduled to be held in Utrecht, the Netherlands from October 17 to 21, 2026.
2026.inlgmeeting.org
September 2, 2026 at 11:26 AM
Here's the list of accepted papers for #INLG2026: 2026.inlgmeeting.org/accepted-pap...
Much to see at the conference, but as always this will be a single-track program. I love this set-up, as it creates common ground for attendees to discuss what they've seen.
Registration is open now!
#NLP #AI
Much to see at the conference, but as always this will be a single-track program. I love this set-up, as it creates common ground for attendees to discuss what they've seen.
Registration is open now!
#NLP #AI
I am looking for public motivations of AI use for marketing purposes. If you see any examples, please send them to me.
Here's an example from the brand Marc O'Polo:
"We make targeted use of AI-generated images - in areas where they help us create more diverse visual worlds ..."
#AI #Marketing
1/2
Here's an example from the brand Marc O'Polo:
"We make targeted use of AI-generated images - in areas where they help us create more diverse visual worlds ..."
#AI #Marketing
1/2
August 27, 2026 at 9:30 PM
I am looking for public motivations of AI use for marketing purposes. If you see any examples, please send them to me.
Here's an example from the brand Marc O'Polo:
"We make targeted use of AI-generated images - in areas where they help us create more diverse visual worlds ..."
#AI #Marketing
1/2
Here's an example from the brand Marc O'Polo:
"We make targeted use of AI-generated images - in areas where they help us create more diverse visual worlds ..."
#AI #Marketing
1/2
Reposted by Emiel van Miltenburg
**Please repost** If you're enjoying Paper Skygest -- our personalized feed of academic content on Bluesky -- we'd appreciate you reposting this! We’ve found that the most effective way for us to reach new users and communities is through users sharing it with their network
August 19, 2025 at 5:15 PM
**Please repost** If you're enjoying Paper Skygest -- our personalized feed of academic content on Bluesky -- we'd appreciate you reposting this! We’ve found that the most effective way for us to reach new users and communities is through users sharing it with their network
Our book review of @ehudreiter.bsky.social 's book on Natural Language Generation is finally out: direct.mit.edu/coli/article...
#NLProc
#NLProc
Natural Language Generation by Ehud Reiter
direct.mit.edu
July 8, 2026 at 9:55 PM
Our book review of @ehudreiter.bsky.social 's book on Natural Language Generation is finally out: direct.mit.edu/coli/article...
#NLProc
#NLProc
This week the decisions for #COLM are out (8th of July) and the #EMNLP author response period has started (July 7-13).
If you're looking for an alternative #NLProc venue: please consider #INLG! (Either via ARR or direct submissions.)
Submission deadline is July 15.
See: 2026.inlgmeeting.org
If you're looking for an alternative #NLProc venue: please consider #INLG! (Either via ARR or direct submissions.)
Submission deadline is July 15.
See: 2026.inlgmeeting.org
INLG2026
The 19th International Natural Language Generation Conference is scheduled to be held in Utrecht, the Netherlands from October 17 to 21, 2026.
2026.inlgmeeting.org
July 7, 2026 at 9:25 PM
This week the decisions for #COLM are out (8th of July) and the #EMNLP author response period has started (July 7-13).
If you're looking for an alternative #NLProc venue: please consider #INLG! (Either via ARR or direct submissions.)
Submission deadline is July 15.
See: 2026.inlgmeeting.org
If you're looking for an alternative #NLProc venue: please consider #INLG! (Either via ARR or direct submissions.)
Submission deadline is July 15.
See: 2026.inlgmeeting.org
Good to know
* INLG also welcomes dual submissions.
* The conference is held right before & relatively close to EMNLP, so you could attend both.
* You can either submit directly (deadline: July 15) or commit a reviewed paper from ARR.
* INLG also welcomes dual submissions.
* The conference is held right before & relatively close to EMNLP, so you could attend both.
* You can either submit directly (deadline: July 15) or commit a reviewed paper from ARR.
INLG (@inlg.bsky.social) submissions are now open!
Please submit all of your work on Natural Language Generation.
Submit systems, demos, experiments, position papers, squibs, linguistic analyses, as long as it is NLG-related.
For more information, see: 2026.inlgmeeting.org
#NLProc
Please submit all of your work on Natural Language Generation.
Submit systems, demos, experiments, position papers, squibs, linguistic analyses, as long as it is NLG-related.
For more information, see: 2026.inlgmeeting.org
#NLProc
INLG2026
The 19th International Natural Language Generation Conference is scheduled to be held in Utrecht, the Netherlands from October 17 to 21, 2026.
2026.inlgmeeting.org
June 26, 2026 at 9:59 AM
Good to know
* INLG also welcomes dual submissions.
* The conference is held right before & relatively close to EMNLP, so you could attend both.
* You can either submit directly (deadline: July 15) or commit a reviewed paper from ARR.
* INLG also welcomes dual submissions.
* The conference is held right before & relatively close to EMNLP, so you could attend both.
* You can either submit directly (deadline: July 15) or commit a reviewed paper from ARR.
INLG (@inlg.bsky.social) submissions are now open!
Please submit all of your work on Natural Language Generation.
Submit systems, demos, experiments, position papers, squibs, linguistic analyses, as long as it is NLG-related.
For more information, see: 2026.inlgmeeting.org
#NLProc
Please submit all of your work on Natural Language Generation.
Submit systems, demos, experiments, position papers, squibs, linguistic analyses, as long as it is NLG-related.
For more information, see: 2026.inlgmeeting.org
#NLProc
INLG2026
The 19th International Natural Language Generation Conference is scheduled to be held in Utrecht, the Netherlands from October 17 to 21, 2026.
2026.inlgmeeting.org
June 26, 2026 at 9:55 AM
INLG (@inlg.bsky.social) submissions are now open!
Please submit all of your work on Natural Language Generation.
Submit systems, demos, experiments, position papers, squibs, linguistic analyses, as long as it is NLG-related.
For more information, see: 2026.inlgmeeting.org
#NLProc
Please submit all of your work on Natural Language Generation.
Submit systems, demos, experiments, position papers, squibs, linguistic analyses, as long as it is NLG-related.
For more information, see: 2026.inlgmeeting.org
#NLProc
Reposted by Emiel van Miltenburg
📣 Announcing the release of the 🕊️ Annotated Encyclical 🕊️ from the ethics & society folks at @hf.co. Includes citations to relevant academic work.
Very much a WIP. Please add work we haven't added yet!
huggingface.co/spaces/socie...
Very much a WIP. Please add work we haven't added yet!
huggingface.co/spaces/socie...
The Annotated Encyclical - a Hugging Face Space by society-ethics
Magnifica Humanitas, annotated with AI-ethics research
huggingface.co
June 1, 2026 at 8:44 AM
📣 Announcing the release of the 🕊️ Annotated Encyclical 🕊️ from the ethics & society folks at @hf.co. Includes citations to relevant academic work.
Very much a WIP. Please add work we haven't added yet!
huggingface.co/spaces/socie...
Very much a WIP. Please add work we haven't added yet!
huggingface.co/spaces/socie...
It is somewhat disappointing that the flagship journals of NLP (CL and TACL) only publish PDFs. It would be great if we could somehow move to include HTML publications as well.
More generally, the accessibility of documents in the ACL Anthology is limited. We're building massive technical debt.
More generally, the accessibility of documents in the ACL Anthology is limited. We're building massive technical debt.
May 13, 2026 at 7:30 AM
It is somewhat disappointing that the flagship journals of NLP (CL and TACL) only publish PDFs. It would be great if we could somehow move to include HTML publications as well.
More generally, the accessibility of documents in the ACL Anthology is limited. We're building massive technical debt.
More generally, the accessibility of documents in the ACL Anthology is limited. We're building massive technical debt.
The International conference on Natural Language Generation (INLG) just issued the first Call For Papers: 2026.inlgmeeting.org/calls.html
#nlproc
#nlproc
INLG2026
The 19th International Natural Language Generation Conference is scheduled to be held in Utrecht, the Netherlands from October 17 to 21, 2026.
2026.inlgmeeting.org
May 10, 2026 at 7:51 PM
The International conference on Natural Language Generation (INLG) just issued the first Call For Papers: 2026.inlgmeeting.org/calls.html
#nlproc
#nlproc
Reposted by Emiel van Miltenburg
In a post-CHI blog post, I talk about what I believe technology like the Anthropic Interviewer will mean for qualitative research.
doomscrollingbabel.manoel.xyz/p/qualitativ...
doomscrollingbabel.manoel.xyz/p/qualitativ...
April 18, 2026 at 1:44 PM
In a post-CHI blog post, I talk about what I believe technology like the Anthropic Interviewer will mean for qualitative research.
doomscrollingbabel.manoel.xyz/p/qualitativ...
doomscrollingbabel.manoel.xyz/p/qualitativ...
Not the best idea ever to announce this during the Bluesky blackout..
New paper on LLMs and research methodology: Justify your prompts! direct.mit.edu/coli/article...
#nlproc
#nlproc
Justify Your Prompts!
Abstract. When you use a large language model (LLM) in your research, you often need to formulate a prompt to elicit some relevant output from the LLM. This step is challenging since (1) LLMs are know...
direct.mit.edu
April 18, 2026 at 7:54 AM
Not the best idea ever to announce this during the Bluesky blackout..
New paper on LLMs and research methodology: Justify your prompts! direct.mit.edu/coli/article...
#nlproc
#nlproc
Justify Your Prompts!
Abstract. When you use a large language model (LLM) in your research, you often need to formulate a prompt to elicit some relevant output from the LLM. This step is challenging since (1) LLMs are know...
direct.mit.edu
April 16, 2026 at 3:17 PM
New paper on LLMs and research methodology: Justify your prompts! direct.mit.edu/coli/article...
#nlproc
#nlproc
Reposted by Emiel van Miltenburg
Noce paper on how well benchmarks cover what people do at work
arxiv.org/abs/2603.01203
Quote
"these observations suggest that agent benchmarking effort is driven less by alignment with real-world employment structure or economic value, and more by methodological convenience."
arxiv.org/abs/2603.01203
Quote
"these observations suggest that agent benchmarking effort is driven less by alignment with real-world employment structure or economic value, and more by methodological convenience."
How Well Does Agent Development Reflect Real-World Work?
AI agents are increasingly developed and evaluated on benchmarks relevant to human work, yet it remains unclear how representative these benchmarking efforts are of the labor market as a whole. In thi...
arxiv.org
March 26, 2026 at 9:18 AM
Noce paper on how well benchmarks cover what people do at work
arxiv.org/abs/2603.01203
Quote
"these observations suggest that agent benchmarking effort is driven less by alignment with real-world employment structure or economic value, and more by methodological convenience."
arxiv.org/abs/2603.01203
Quote
"these observations suggest that agent benchmarking effort is driven less by alignment with real-world employment structure or economic value, and more by methodological convenience."
@ai2.bsky.social I'm confused by the OLMoTrace paper. The paper says that the trace feature is useful for "Fact checking" (see image), but the Limitations section notes: "The
retrieved documents should not be interpreted as [...] supporting evidence or citations for the LM output."
A contradiction?
retrieved documents should not be interpreted as [...] supporting evidence or citations for the LM output."
A contradiction?
March 26, 2026 at 9:30 AM
@ai2.bsky.social I'm confused by the OLMoTrace paper. The paper says that the trace feature is useful for "Fact checking" (see image), but the Limitations section notes: "The
retrieved documents should not be interpreted as [...] supporting evidence or citations for the LM output."
A contradiction?
retrieved documents should not be interpreted as [...] supporting evidence or citations for the LM output."
A contradiction?
Article is in Dutch, but maybe understandable via Google Translate.
TL;DR: AI poetry is used in 3 different ways.
1. To study progress in creative computing;
2. To explore new literary forms and to see how people interpret those;
3. To (deceptively) market AI with appeals to its 'humanity.'
TL;DR: AI poetry is used in 3 different ways.
1. To study progress in creative computing;
2. To explore new literary forms and to see how people interpret those;
3. To (deceptively) market AI with appeals to its 'humanity.'
Nieuw artikel over Poëzie en kunstmatige intelligentie: www.aup-online.com/content/jour...
(Open-access versie hier: research.tilburguniversity.edu/en/publicati...)
(Open-access versie hier: research.tilburguniversity.edu/en/publicati...)
Poëzie en Kunstmatige Intelligentie: Toetssteen, Proeftuin, Marketingtruc | Amsterdam University Press Journals Online
Abstract
Automatically generated poetry has a long history, dating back at least to John Peter’s (1677) algorithm that was able to produce almost 600,000 Latin lines of poetry. Attention to this topic...
www.aup-online.com
March 5, 2026 at 10:53 PM
Article is in Dutch, but maybe understandable via Google Translate.
TL;DR: AI poetry is used in 3 different ways.
1. To study progress in creative computing;
2. To explore new literary forms and to see how people interpret those;
3. To (deceptively) market AI with appeals to its 'humanity.'
TL;DR: AI poetry is used in 3 different ways.
1. To study progress in creative computing;
2. To explore new literary forms and to see how people interpret those;
3. To (deceptively) market AI with appeals to its 'humanity.'
Nieuw artikel over Poëzie en kunstmatige intelligentie: www.aup-online.com/content/jour...
(Open-access versie hier: research.tilburguniversity.edu/en/publicati...)
(Open-access versie hier: research.tilburguniversity.edu/en/publicati...)
Poëzie en Kunstmatige Intelligentie: Toetssteen, Proeftuin, Marketingtruc | Amsterdam University Press Journals Online
Abstract
Automatically generated poetry has a long history, dating back at least to John Peter’s (1677) algorithm that was able to produce almost 600,000 Latin lines of poetry. Attention to this topic...
www.aup-online.com
March 5, 2026 at 3:29 PM
Nieuw artikel over Poëzie en kunstmatige intelligentie: www.aup-online.com/content/jour...
(Open-access versie hier: research.tilburguniversity.edu/en/publicati...)
(Open-access versie hier: research.tilburguniversity.edu/en/publicati...)
I should have known this: not all innovations are improvements.
PSA: Today I learned that quizzes created in the Canvas learning management system using the New Quiz Builder don't allow you to export all student answers to Excel/CSV. This has been a problem since 2021.
Don't use the new quiz builder. Use the old one.
community.instructure.com/en/discussio...
Don't use the new quiz builder. Use the old one.
community.instructure.com/en/discussio...
Export All Quiz Answers from All Students as a CSV or EXCEL spreadsheet or XML data structure - Instructure Community
We are developing new psychometric methods for student response data analysis. Is there a way to export the individual responses of all students to all questions for a quiz such as a CSV or EXCEL or X...
community.instructure.com
January 30, 2026 at 10:28 AM
I should have known this: not all innovations are improvements.
PSA: Today I learned that quizzes created in the Canvas learning management system using the New Quiz Builder don't allow you to export all student answers to Excel/CSV. This has been a problem since 2021.
Don't use the new quiz builder. Use the old one.
community.instructure.com/en/discussio...
Don't use the new quiz builder. Use the old one.
community.instructure.com/en/discussio...
Export All Quiz Answers from All Students as a CSV or EXCEL spreadsheet or XML data structure - Instructure Community
We are developing new psychometric methods for student response data analysis. Is there a way to export the individual responses of all students to all questions for a quiz such as a CSV or EXCEL or X...
community.instructure.com
January 30, 2026 at 10:27 AM
PSA: Today I learned that quizzes created in the Canvas learning management system using the New Quiz Builder don't allow you to export all student answers to Excel/CSV. This has been a problem since 2021.
Don't use the new quiz builder. Use the old one.
community.instructure.com/en/discussio...
Don't use the new quiz builder. Use the old one.
community.instructure.com/en/discussio...
Surprising omission: the @aclrollingreview.bsky.social website does not have an easily findable button to sign up as a reviewer. Seems like a missed opportunity.
January 23, 2026 at 10:42 AM
Surprising omission: the @aclrollingreview.bsky.social website does not have an easily findable button to sign up as a reviewer. Seems like a missed opportunity.
Some years ago, I bought Joseph Weizenbaum's book on Computer Power and Human Reason for a couple of dollars. Nice to have a classic work on computers and society.
Following the AI boom, the price of secondhand copies has skyrocketed: more than 100 dollars for a used copy!
Following the AI boom, the price of secondhand copies has skyrocketed: more than 100 dollars for a used copy!
September 24, 2025 at 8:54 AM
Some years ago, I bought Joseph Weizenbaum's book on Computer Power and Human Reason for a couple of dollars. Nice to have a classic work on computers and society.
Following the AI boom, the price of secondhand copies has skyrocketed: more than 100 dollars for a used copy!
Following the AI boom, the price of secondhand copies has skyrocketed: more than 100 dollars for a used copy!
Nice essay on AI ethics by @frank.computer: www.frank.computer/blog/2025/05...
Stop saying that AI is just a tool and it only matters how it is used
I’m tired of this phrase and this simple way of thinking about tools. This blog post is a wandering train of thought on the topic of what tools are and why it matters to be even slightly more mature i...
www.frank.computer
August 25, 2025 at 8:15 AM
Nice essay on AI ethics by @frank.computer: www.frank.computer/blog/2025/05...
We just published a position paper on the evaluation of dialog systems, roughly asking:
1. Why don't we talk more about usage requirements for evaluation metrics?
2. Should we only adapt metrics to dialog, or can we also adapt dialog to suit metrics?
URL: aclanthology.org/2025.gem-1.18/
#NLProc
1. Why don't we talk more about usage requirements for evaluation metrics?
2. Should we only adapt metrics to dialog, or can we also adapt dialog to suit metrics?
URL: aclanthology.org/2025.gem-1.18/
#NLProc
Measure only what is measurable: towards conversation requirements for evaluating task-oriented dialogue systems
Emiel Van Miltenburg, Anouck Braggaar, Emmelyn Croes, Florian Kunneman, Christine Liebrecht, Gabriella Martijn. Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM²). 2025.
aclanthology.org
August 22, 2025 at 1:07 PM
We just published a position paper on the evaluation of dialog systems, roughly asking:
1. Why don't we talk more about usage requirements for evaluation metrics?
2. Should we only adapt metrics to dialog, or can we also adapt dialog to suit metrics?
URL: aclanthology.org/2025.gem-1.18/
#NLProc
1. Why don't we talk more about usage requirements for evaluation metrics?
2. Should we only adapt metrics to dialog, or can we also adapt dialog to suit metrics?
URL: aclanthology.org/2025.gem-1.18/
#NLProc
I'm looking for studies on the mood/atmosphere/affective dimensions of photographs, but it's hard to find relevant work.
Any recommendations?
Any recommendations?
July 17, 2025 at 7:46 AM
I'm looking for studies on the mood/atmosphere/affective dimensions of photographs, but it's hard to find relevant work.
Any recommendations?
Any recommendations?