Emiel van Miltenburg
@evanmiltenburg.bsky.social
Assistant professor in computational linguistics/nlp. Interested in research methodology, ethics, multimodality, and accessibility.
"... respond more quickly to ideas, and expand our creative possibilities. However, people always make the final decisions: about style, attitude, and what we want to show."
I find these motivations of AI use fascinating, but I need more examples to study them properly. Please share any examples!
I find these motivations of AI use fascinating, but I need more examples to study them properly. Please share any examples!
August 27, 2026 at 9:31 PM
"... respond more quickly to ideas, and expand our creative possibilities. However, people always make the final decisions: about style, attitude, and what we want to show."
I find these motivations of AI use fascinating, but I need more examples to study them properly. Please share any examples!
I find these motivations of AI use fascinating, but I need more examples to study them properly. Please share any examples!
Link: www.microsoft.com/en-us/resear...
And this paper by Maartje de Meulder on Deafness and AI: arxiv.org/abs/2505.02519
And this paper by Maartje de Meulder on Deafness and AI: arxiv.org/abs/2505.02519
August 26, 2026 at 3:15 PM
Link: www.microsoft.com/en-us/resear...
And this paper by Maartje de Meulder on Deafness and AI: arxiv.org/abs/2505.02519
And this paper by Maartje de Meulder on Deafness and AI: arxiv.org/abs/2505.02519
In this context you might like:
* This panel discussion with blind technology advocates on the use of computer vision technology. IIRC Chancey Fleet makes a point about blind people not wanting to be used as an excuse to advance technology that is used for surveillance. Deafness may be similar
1/2
* This panel discussion with blind technology advocates on the use of computer vision technology. IIRC Chancey Fleet makes a point about blind people not wanting to be used as an excuse to advance technology that is used for surveillance. Deafness may be similar
1/2
August 26, 2026 at 3:14 PM
In this context you might like:
* This panel discussion with blind technology advocates on the use of computer vision technology. IIRC Chancey Fleet makes a point about blind people not wanting to be used as an excuse to advance technology that is used for surveillance. Deafness may be similar
1/2
* This panel discussion with blind technology advocates on the use of computer vision technology. IIRC Chancey Fleet makes a point about blind people not wanting to be used as an excuse to advance technology that is used for surveillance. Deafness may be similar
1/2
INLG focuses on all aspects of language generation, and is an appropriate venue for work on LLMs, rule-based generation, as well as human language production.
We have a great community, with a nice balance between industry and academia. Reviews are generally constructive & useful. Keynotes TBA soon
We have a great community, with a nice balance between industry and academia. Reviews are generally constructive & useful. Keynotes TBA soon
July 7, 2026 at 9:30 PM
INLG focuses on all aspects of language generation, and is an appropriate venue for work on LLMs, rule-based generation, as well as human language production.
We have a great community, with a nice balance between industry and academia. Reviews are generally constructive & useful. Keynotes TBA soon
We have a great community, with a nice balance between industry and academia. Reviews are generally constructive & useful. Keynotes TBA soon
Could be that early access is pdf and the html version is only published later. Not ideal from an accessibility perspective, but good to know html will be there eventually.
May 14, 2026 at 6:07 PM
Could be that early access is pdf and the html version is only published later. Not ideal from an accessibility perspective, but good to know html will be there eventually.
Not for our paper, published this year: direct.mit.edu/coli/article...
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
May 13, 2026 at 9:19 AM
Not for our paper, published this year: direct.mit.edu/coli/article...
You can also open many pdfs in Word and then do a diff in Word. Works better than you would expect!
April 17, 2026 at 2:26 PM
You can also open many pdfs in Word and then do a diff in Word. Works better than you would expect!
Our analysis is based on this article by @lakens.bsky.social: online.ucpress.edu/collabra/art...
The original article discusses arguments that are used in empirical research to justify the choice of sample size. We translated those justification strategies to the domain of LLMs.
The original article discusses arguments that are used in empirical research to justify the choice of sample size. We translated those justification strategies to the domain of LLMs.
Sample Size Justification
An important step when designing an empirical study is to justify the sample size that will be collected. The key aim of a sample size justification for such studies is to explain how the collected da...
online.ucpress.edu
April 17, 2026 at 6:57 AM
Our analysis is based on this article by @lakens.bsky.social: online.ucpress.edu/collabra/art...
The original article discusses arguments that are used in empirical research to justify the choice of sample size. We translated those justification strategies to the domain of LLMs.
The original article discusses arguments that are used in empirical research to justify the choice of sample size. We translated those justification strategies to the domain of LLMs.
But yeah: bring back live tweeting! So nice to at least get a sense of what's being discussed at workshops and conferences you're not attending & be able to join the conversation.
March 16, 2026 at 9:08 AM
But yeah: bring back live tweeting! So nice to at least get a sense of what's being discussed at workshops and conferences you're not attending & be able to join the conversation.
That, and just feeling like you're all sitting in a pub together. Now it's all much more dispersed, with people on BlueSky, Mastodon, LinkedIn, Discord (SIGGEN has a community Discord server), etc.
I haven't met most #NLProc people in real life, but our conversations really shaped my work.
I haven't met most #NLProc people in real life, but our conversations really shaped my work.
March 16, 2026 at 9:07 AM
That, and just feeling like you're all sitting in a pub together. Now it's all much more dispersed, with people on BlueSky, Mastodon, LinkedIn, Discord (SIGGEN has a community Discord server), etc.
I haven't met most #NLProc people in real life, but our conversations really shaped my work.
I haven't met most #NLProc people in real life, but our conversations really shaped my work.