Tootfinder

Opt-in global Mastodon full text search. Join the index!

@arXiv_csCL_bot@mastoxiv.page
2025-09-05 10:11:41

What if I ask in \textit{alia lingua}? Measuring Functional Similarity Across Languages
Debangan Mishra, Arihant Rastogi, Agyeya Negi, Shashwat Goel, Ponnurangam Kumaraguru
arxiv.org/abs/2509.04032

What if I ask in \textit{alia lingua}? Measuring Functional Similarity Across Languages
How similar are model outputs across languages? In this work, we study this question using a recently proposed model similarity metric $κ_p$ applied to 20 languages and 47 subjects in GlobalMMLU. Our analysis reveals that a model's responses become increasingly consistent across languages as its size and capability grow. Interestingly, models exhibit greater cross-lingual consistency within themselves than agreement with other models prompted in the same language. These results highlight not o…

@v_i_o_l_a@openbiblio.social
2025-09-08 08:37:37

"Multilingual Scholarly Publishing and Artificial Intelligence Translation Tools: Weighing Social Justice and Climate Justice"
doi.org/10.3998/jep.7100

Multilingual Scholarly Publishing and Artificial Intelligence Translation Tools: Weighing Social Justice and Climate Justice
The use of English as a lingua franca for scholarly publishing has created inequities and is leading to a social justice movement to develop a more multilingual scholarly publishing ecosystem. However, implementing multilingualism is complex, and researchers and publishers are investigating the potential of AI translation tools for supporting linguistic diversity. At the same time, the climate justice movement is beginning to reveal some of the environmental and human costs associated with AI t…

@BBC3MusicBot@mastodonapp.uk
2025-10-18 06:42:37

🇺🇦 #NowPlaying on BBCRadio3's #Breakfast
Anton Bruckner, Sigvards Kļava & Latvian Radio Choir:
🎵 Pange lingua, WAB 33
#AntonBruckner #SigvardsKļava #LatvianRadioChoir
open.spotify.com/track/3zjg2nJ

@arXiv_csCL_bot@mastoxiv.page
2025-09-03 14:44:43

The Forgotten Code: Validating a Century-Old Translation System with AI
Jean-Marie Le Ray
arxiv.org/abs/2509.02506 arxiv.org/pdf/2509.02506…

The Forgotten Code: Validating a Century-Old Translation System with AI
A pioneering rule-based mechanical translation system (precursor of modern RBMTs) was first presented in December 1929 by its inventor, Federico Pucci, who later published the full method in a book titled "Il traduttore meccanico ed il metodo per corrispondersi fra Europei conoscendo ciascuno solo la propria lingua: Parte I", in Salerno (Italy), in 1931. This study illustrates how AI breathes new life into the system of international keys and ideograms devised by Pucci to translate from/into an…

@BBC3MusicBot@mastodonapp.uk
2025-09-13 13:48:27

🇺🇦 #NowPlaying on BBCRadio3's #RecordReview
Modest Mussorgsky & Alfred Brendel:
🎵 Pictures at an Exhibition - VIII: Con mortuis in lingua mortua. Andante non troppo, con lament
#ModestMussorgsky #AlfredBrendel
open.spotify.com/track/5uvKLDR

@rgiuse@mastodon.uno
2025-08-23 06:11:03

Se non lo avessi capito questi epiteti indipendentemente dalla lingua o dalla sfumatura usata hanno rotto il caxxo da un bel po.