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
Website: sites.google.com/view/gitt2026
Use tag #GITT2026
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!
💭 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!
June 24, 2025 at 5:51 AM
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!
💭 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!
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
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
Experiments using mGeNTE as reference arxiv.org/abs/2501.09409
June 23, 2025 at 2:17 PM
Experiments using mGeNTE as reference arxiv.org/abs/2501.09409
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
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
Work on LLM-as-judge suggests this could be useful for GNT evaluation as well
June 23, 2025 at 2:11 PM
Work on LLM-as-judge suggests this could be useful for GNT evaluation as well
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
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
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
Not one single solution for gender neutral translation (GNT) (tradeoff adequacy/fluency?) making GNT a complex evaluation task
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
June 23, 2025 at 2:07 PM
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
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
Gender tags can be used in training! Postprocessing can help in time sensitive situations, but can be dangerous too, not always useful
Some attempted strategies: style indication alone not enough, few shot and style guide additions helped
June 23, 2025 at 12:07 PM
Some attempted strategies: style indication alone not enough, few shot and style guide additions helped
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
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"
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
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
Great crowd participation! 👌🔥 Training, teaching, finetuning, data, prompting and more as potential solutions
June 23, 2025 at 11:58 AM
Great crowd participation! 👌🔥 Training, teaching, finetuning, data, prompting and more as potential solutions
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
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
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
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!
Good keynotes use inspirations quotes from others. Great keynotes use inspirational quotes from themselves 👌
June 23, 2025 at 11:40 AM
Good keynotes use inspirations quotes from others. Great keynotes use inspirational quotes from themselves 👌
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
June 23, 2025 at 11:39 AM
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
🔑🎵 Our keynote speaker Cristina Anselmi sharing localisation industry perspectives on optimising AI for inclusivity 🤩
June 23, 2025 at 11:36 AM
🔑🎵 Our keynote speaker Cristina Anselmi sharing localisation industry perspectives on optimising AI for inclusivity 🤩
Evaluation clearly still shows issues and how challenging this is in real world scenarios. Hillary and colleagues are open to collaborate with anyone willing to help tackle this issue in future work 🤝
June 23, 2025 at 10:08 AM
Evaluation clearly still shows issues and how challenging this is in real world scenarios. Hillary and colleagues are open to collaborate with anyone willing to help tackle this issue in future work 🤝
Some response to actively ambiguous sentences, but no consistency across languages and systems.
June 23, 2025 at 10:05 AM
Some response to actively ambiguous sentences, but no consistency across languages and systems.
Baseline: neutral translation when gender is known shows variance within languages across systems. Ambiguous scenarios show strong default masculine translation, no increase in neutral translations
June 23, 2025 at 10:03 AM
Baseline: neutral translation when gender is known shows variance within languages across systems. Ambiguous scenarios show strong default masculine translation, no increase in neutral translations