The combination of dynamic user-generated content and multilingual aspects is particularly prominent in Wiki sites. Wikis have gained increased popularity over the last few years as a means of collaborative content creation as they allow users to set up and edit web pages directly. A growing number of organizations use Wikis as an efficient means to provide and maintain information across several sites. Currently, multilingual Wikis rely on users to manually translate different Wiki pages on the same subject. This is not only a time-consuming procedure but also the source of many inconsistencies, as users update the different language versions separately, and every update would require translators to compare the different language versions and synchronize the updates. The overall aim of the CoSyne project is to automate the dynamic multilingual synchronization process of Wikis.
ποΈ Yesterday at #LREC2026, Palma de Mallorca!
@lina_conti presented "Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation" at the poster session.
πPaper:
π»Code: https://github.com/lina-conti/voice-bias-coreference
#SpeechTranslation #NLProc
How does the granularity of speech-text pairs impact SpeechLLM performance, and what is the optimal way to interleave tokens? Furthermore, what are the best practices for generating synthetic data to boost training?π§
ποΈ Our paper on connecting Speech Foundation Models with LLMs is featured in the SpeechLMM Training Journal on Weights & Biases.
Read it π https://bit.ly/4svG7ll
SpeechLMM 2.0 coming this summer. π
#Meetween #SpeechLMM #AI #NLP