iiinova — where your digital self keeps evolving

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

And that's a wrap on #GITT2026 Thanks to all the wonderful people for attending, our brilliant keynotes and presenters for sharing their insights, and our sponsors for making this happen. See you at the reception! 🥂 (and maybe next year? 😉)

065

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Students who received training (even very short) on gender-fair language made fewer misgendering mistakes for German and French. Fluency is impacted a bit, but there is an obvious learning curve, with fluency improving as the conversation goes on #GITT2026

030

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Switching gears to a project with Laura Robaey on gender fair language in interpreted interactions with service providers - how do student interpreters handle this and how can we prepare them for this kind of language? #GITT2026

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

People are increasingly familiar with nonbinary pronouns and attitudes are somewhat more positive through time as well, but usage remains stable/low. More accepted for generic use than for nonbinary reference. Introduction seems slower in Dutch and French (frequent masculine generics?) #GITT2026

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Compared to the naming task, when asked to describe an employee at company X, gender is mentioned less frequently and gender representations are more mixed / diverse. Compared to men, women and nonbinary people are more likely to mention gender #GITT2026

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

What happens to mental representation? Green=male, red=female, blue=ambiguous descriptions depending on pronouns used in descriptions. Gender inclusive pronouns lead to more diverse representation for women, but did not eliminate male bias in men #GITT2026

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Similar results for inclusive pronouns for reference to unknown referent in employee guidelines: no impact on content question accuracy - somewhat more obvious differences for French but still need to be interpreted with caution: what is the practical implication? #GITT2026

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Nonbinary pronouns for nonbinary referent had no impact on accuracy compared to other strategies, but some other differences detected #GITT2026

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Pronouns are intriguing as linguistic phenomenon: do they really impact comprehension? Do they actually reduce male bias? To what extent have they been successfully introduced in language? Which factors influence this? Big WEAVE project on small words tries to answer these questions!

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Gender neutral pronouns are introduced into languages in different ways and serve different purposes (specific nonbinary reference, specific reference to unknown referent, generic reference to people in general) #GITT2026

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

And last but not least, our closing keynote, Sofie Decock, ready to tell us all about gender-neutral pronouns and inclusive interpreting at #GITT2026

9122

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Poster sessions in full swing at #GITT2026 - will continue a little after the coffee break as well ☕

132

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Banger line to wrap up with: "although speech technologies themselves are not inclusive, you can use them to make a more inclusive society" #GITT2026

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Crowdfunding now live for ASR for live captioning for people with a speech impairment at www.supporttudelft.nl/project/veel...

020

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Dysarthric speech remains challenging for humans and systems, unless we add data augmentation - fine tuned systems go down to 20-30 WER #GITT2026

020

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

But what about human listeners? Brand new work (ongoing) shows that word error rate is really high for human listeners as well 👀👀 Google Telephony outperformed humans on diverse speech #GITT2026

020

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Different types of data augmentation in practice #GITT2026 massive improvements (word error rate reductions) are possible for both native and non-native speech.

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Different types of diversity need different types of data augmentation - these findings didn't make reviewers happy but have been verified repeatedly! #GITT2026

030

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Possible solutions: data augmentation (SpecAugment, speed, volume, pitch changes, voice conversion) or different training strategies (fine-tuning, domain-adversarial training, multi-task learning)

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Architectures and language matter - can lead to very different bias patterns #GITT2026 some similarities and differences across languages "bias is there, but we don't really know what the origin is"

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Can we locate origin of bias so we can mitigate it? Study with Dutch and Flemish speech and with Mandarin. Trained on CGN, tested on Jasmin, some differences between Dutch and Flemish. taalmaterialen.ivdnt.org/download/tst...

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

We need actually inclusive speech technology. Biggest issues = data, bias against different speaker groups, lack of definition of fairness / bias / inclusiveness #GITT2026

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Speech technology only works for some of the 7000+ languages in the world and only for standard speech, whereas a lot of speech is actually diverse (-18, +60, speech impediments, different accents, etc.) - can impact anything from healthcare to education to accessibility #GITT2026

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

After a lovely lunch break with lively discussion, our second keynote of the day, @odettes.bsky.social now presenting on inclusive speech technology at #GITT2026 🤩

1131

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

@amelija166mp.bsky.social on gender bias in translated product reviews and Deniz Albayrak on WinoTR #GITT2026

032

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Sophie Hennuy presenting the Inclupedie (see www.inclupedie.eu) and Marie Dewulf on a real world corpus for gender bias in the webcare domain #GITT2026

031

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Poster boasters at #GITT2026 ! 🤩 Come check our these brilliant posters in the afternoon! First up @lexiconista.bsky.social introducing Fairslator and @elenigkove.bsky.social introducing ReGender - gender fair rewriting is hot 🔥🔥🔥

320

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Complexity of the data: not a lot of variety in the emotions to be detected. Focus on 'love' ❤️ - humans more likely to translate 'love' reviews as feminine. LLMs still default to masculine, with the exception of Llama #GITT2026

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Does source text emotion function as an implicit gender cue, both in human translation and LLMs (focus on binary gender given the Russian language)? Text = English Amazon reviews, translators and LLM did not receive gender-specific instructions #GITT2026

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Shushen Manakhimova presenting joint work with Ekaterina Lapahinova-Koltunski at #GITT2026 on the link between emotional stereotypes and gender - could these influence the machine translation process?

220

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Consistency and automatic labeling are similar across models. Failure happens e.g. across unit boundaries or for compound nouns. Masculine bias, inefficient strategies and incoherence issues remain #GITT2026

020

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Reasoning models seem to perform better than non-reasoning ones (or at least "fail less often" 😉) #GITT2026

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Reasoning helps when going from binary input to nonbinary output, nonbinary input leads to more chaos (but reasoning can mitigate some unwanted effects)

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

LegISTyr test set focuses on legal terminology and tests the impact of strategy used in the source (binary or non-binary inclusive) on target rendering in LLM workflow (with and without reasoning) #GITT2026

010

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Paolo Di Natalie's very first PhD presentation here at #GITT2026 focusing on the real use case of Italian-German fully bilingual context and gender fair translation in South Tyrol (Italy)

431

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Another call for human intervention: queer misrepresentation happens by different kinds of technology, albeit in different ways #GITT2026

000

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

LLM mostly leads to misgendering (only into feminine!) and some intriguing intralingual and interlingual calques or hybrid morpholgical hallucinations

000

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

NMT usually leads to pro-drop or misgendering by binary translations (also this presentation has a lot of brilliant memes but typing and taking pictures at the same time is hard - you'll have to join us in the room next edition for the full experience 😉) #GITT2026

000

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Queer novel translation (Schwindel) with 3 different strategies, followed by annotation of bias and misgendering, translation failures, and non-binary translation strategies

000

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

#GITT2026 's very own @manuellardelli.bsky.social presenting on nonbinary morphology in a real translation workflow for German and Italian (moving away from the English focus and binary limitations of many gender studies!)

442

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

LLM and WinoMT have similar performance with different weaknesses, aka human annotation and validation remains essential #GITT2026

020

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Results look okay, until you look at the 'unknown' categories: alignment shift, tagging errors, translation variability for WinoMT, forced binary annotation for LLM in linguistic indeterminacy contexts

020

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Process of gender annotation relies on automatic steps in the pipeline which can lead to errors #GITT2026 - to what extent do labels correlate with human annotations and can LLM be used instead?

031

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

As well as the perception of the linguistic strategies used for non-binary referent translation by Dutch audiences:

020

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

@jdaems.bsky.social and team investigated non-binary pronoun translation in Netflix's series 'Sex Education' #GITT2026

030

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

Next on, @jdaems.bsky.social presenting their work on Dutch audience perceptions of human and machine-translated pronouns for non-binary referent in subtitles at #GITT2026

272

GITT 2026 @gitt-workshop.bsky.social · 15/06/2026

A call for slow science, looking for alternatives from the ground up. Back to basics and build everything from the ground up on stronger pillars!

010