GITT 2026
gitt-workshop.bsky.social
GITT 2026
@gitt-workshop.bsky.social
Workshop on Gender-Inclusive Translation Technologies. 4th edition happening at EAMT2026 in Tilburg!
Website: sites.google.com/view/gitt2026
Use tag #GITT2026
Extra shout-out to the battle-hardened crew joining for this round 🔥 @jhackenbuchner.bsky.social @luisabentivogli.bsky.social @jdaems.bsky.social @bsavoldi.bsky.social
December 12, 2025 at 8:35 AM
Results show GPT4-o and Qwen 72B outperforming the baseline classifier and improved accuracy for intermediate reasoning steps. More details in the paper - have a read! 👀 #GITT2025
June 23, 2025 at 2:22 PM
Experiments using mGeNTE as reference arxiv.org/abs/2501.09409
June 23, 2025 at 2:17 PM
RQs: can LLMs identify neutral versus gendered translation? How do we improve the accuracy? Tests on 3 language pairs (English into Italian, Spanish, and German) on sentence and phrase level in monolingual and crosslingual scenarios
June 23, 2025 at 2:15 PM
Work on LLM-as-judge suggests this could be useful for GNT evaluation as well
June 23, 2025 at 2:11 PM
As already raised by our keynote, quality estimation is a great industry need as there is often no time for human evaluation in production, this is particularly tricky for GNT
June 23, 2025 at 2:10 PM
Not one single solution for gender neutral translation (GNT) (tradeoff adequacy/fluency?) making GNT a complex evaluation task
June 23, 2025 at 2:09 PM
June 23, 2025 at 12:14 PM
Summary for inclusive AI: representation, transparency, community input, iteration, respect #GITT2025
June 23, 2025 at 12:12 PM
What should the industry do to be more inclusive? Rely on NB and inclusive language experts, connect with the community, stay updated, train the people (this can be you!), test and iterate
June 23, 2025 at 12:11 PM
Gender tags can be used in training! Postprocessing can help in time sensitive situations, but can be dangerous too, not always useful
June 23, 2025 at 12:09 PM
Some attempted strategies: style indication alone not enough, few shot and style guide additions helped
June 23, 2025 at 12:07 PM
What about prompting? Industry requires everything to work within the pipeline, within the system. You can't have prompts leading to different outputs, it cannot be wrong, it cannot contain hallucinations
June 23, 2025 at 12:05 PM
Microsoft custom translator was finetuned with +/- 5k-10k segments. Because of the specificity of the problem, limited data is enough for improvements. "overfitting in my favor"
June 23, 2025 at 12:03 PM
Perfect data doesn't exist, but data was created with support of experts and generation. Opposite strategies from what you'd want for non-inclusive datasets! Multiple solutions suddenly useful and even necessary
June 23, 2025 at 12:00 PM
Great crowd participation! 👌🔥 Training, teaching, finetuning, data, prompting and more as potential solutions
June 23, 2025 at 11:58 AM
Share your thoughts! #GITT2025 how do we shape AI for inclusive language?
June 23, 2025 at 11:56 AM
Issues for MT: lack of training data (historical data was not inclusive, no representation), association bias, post-editing always necessary, publishing MT output as is can be problematic, tricky for gendered languages, evaluation metrics used in the industry, but might not work for inclusivity
June 23, 2025 at 11:55 AM
Important to consult expert matters and the community. Some specific examples: having the inclusive schwa character on the keyboard for Italian, explicit representation of nonbinary characters, e.g. Dragon Age the Veilguard
June 23, 2025 at 11:51 AM
In big corporations, teams had to be hired specifically for inclusivity, output had to be tested, guidelines needed to be written and constantly updated with rapidly changing language and character representation evolved (games = community, people need to find themselves)
June 23, 2025 at 11:49 AM
Inclusivity has become increasingly important in the industry, especially for younger generations. The path towards inclusive language has a few different steps and inclusivity goes beyond just gender > echoing the idea of intersectionality from the opening notes!
June 23, 2025 at 11:42 AM