GITT 2025
@gitt-workshop.bsky.social
64 followers 75 following 82 posts
Workshop on Gender-Inclusive Translation Technologies. 3rd edition happening at MT Summit 2025! Website: https://sites.google.com/tilburguniversity.edu/gitt2025
Posts Media Videos Starter Packs
gitt-workshop.bsky.social
And that's a wrap on a very hot 🥵 yet very rewarding #GITT2025
💭 We need more languages, better quality estimation, and intersectionality
😍 Thanks to everyone who was there, presented, contributed to the discussion, and helped with practicalities.
🌞 Enjoy the rest of @mtsummit2025.bsky.social!
gitt-workshop.bsky.social
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
gitt-workshop.bsky.social
Experiments using mGeNTE as reference arxiv.org/abs/2501.09409
gitt-workshop.bsky.social
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
gitt-workshop.bsky.social
Work on LLM-as-judge suggests this could be useful for GNT evaluation as well
gitt-workshop.bsky.social
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
gitt-workshop.bsky.social
Not one single solution for gender neutral translation (GNT) (tradeoff adequacy/fluency?) making GNT a complex evaluation task
gitt-workshop.bsky.social
Last but definitely not least: @bsavoldi.bsky.social presenting joint work with @apierg.bsky.social @matteo-negri.bsky.social @luisabentivogli.bsky.social on scalable gender neutral translation evaluation using LLM-as-a-judge at #GITT2025
gitt-workshop.bsky.social
Poster session now happening at #GITT2025 Some really exciting research and potluck discussions happening! 🔥
gitt-workshop.bsky.social
Summary for inclusive AI: representation, transparency, community input, iteration, respect #GITT2025
gitt-workshop.bsky.social
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
gitt-workshop.bsky.social
Gender tags can be used in training! Postprocessing can help in time sensitive situations, but can be dangerous too, not always useful
gitt-workshop.bsky.social
Some attempted strategies: style indication alone not enough, few shot and style guide additions helped
gitt-workshop.bsky.social
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
gitt-workshop.bsky.social
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"
gitt-workshop.bsky.social
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
gitt-workshop.bsky.social
Great crowd participation! 👌🔥 Training, teaching, finetuning, data, prompting and more as potential solutions
gitt-workshop.bsky.social
Share your thoughts! #GITT2025 how do we shape AI for inclusive language?
gitt-workshop.bsky.social
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
gitt-workshop.bsky.social
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
gitt-workshop.bsky.social
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)
gitt-workshop.bsky.social
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!
gitt-workshop.bsky.social
Good keynotes use inspirations quotes from others. Great keynotes use inspirational quotes from themselves 👌
gitt-workshop.bsky.social
Already working on the industry when SMT was the default, not the easiest to use for localisation back then, all the way to NMT and LLM today. "video games today are like a work of art" > not necessarily the easiest match for MT #GITT2025