Tekst achterflap

GITT is set out to focus on gender-inclusive language in translation and cross-lingual scenarios. The workshop brings together researchers from diverse areas, including industry partners, MT practitioners and language professionals. Also, GITT aims to encourage multidisciplinary research that develops and interrogates both solutions and challenges for addressing bias and promoting gender inclusivity in MT and translation tools, including LLM applications for the translation task. The accepted submissions cover a diverse range of topics related to the analysis, measurement, and mitigation of gender bias in (Machine)
Translation, as well as to the investigation of inclusive language. We are glad to attest to the interdisciplinary perspectives and methods represented in GITT submissions. Notably, we observe key trends emerging from this year’s submissions: (i) an increasing use of large language models (LLMs) for bias evaluation and mitigation, (ii) a growing focus on non-binary and gender-inclusive language practices across multiple languages beyond English, and (iii) the application of novel methods — e.g. interpretability tools — to address gender bias.

Beschrijving

GITT is set out to focus on gender-inclusive language in translation and cross-lingual scenarios. The workshop brings together researchers from diverse areas, including industry partners, MT practitioners and language professionals. Also, GITT aims to encourage multidisciplinary research that develops and interrogates both solutions and challenges for addressing bias and promoting gender inclusivity in MT and translation tools, including LLM applications for the translation task. The accepted submissions cover a diverse range of topics related to the analysis, measurement, and mitigation of gender bias in (Machine)
Translation, as well as to the investigation of inclusive language. We are glad to attest to the interdisciplinary perspectives and methods represented in GITT submissions. Notably, we observe key trends emerging from this year’s submissions: (i) an increasing use of large language models (LLMs) for bias evaluation and mitigation, (ii) a growing focus on non-binary and gender-inclusive language practices across multiple languages beyond English, and (iii) the application of novel methods — e.g. interpretability tools — to address gender bias.

Details