MEANING will be concerned with automatically collecting and analysing language data from the WWW on a large scale, and building more comprehensive multilingual lexical knowledge bases to support improved word sense disambiguation (WSD). Current web access applications are based on words; MEANING will open the way for access to the Multilingual Web based on concepts, providing applications with capabilities that significantly exceed those currently available. MEANING will facilitate development of concept-based open domain Internet applications (such as Question/Answering, Cross Lingual Information Retrieval, Summarisation, Text Categorisation, Event Tracking, Information Extraction, Machine Translation, etc.). Furthermore, MEANING will supply a common conceptual structure to Internet documents, thus facilitating knowledge management of web content.
๐ข๐ข We invite proposals for @iwslt 2025 shared tasks!
For further information on this initiative, please refer to
https://iwslt.org/assets/pdfs/IWSLT2025-Call_for_Tasks.pdf
๐
Deadline: September 30th, 2024
@_janius_ @marcfede @shashwatup9k @esalesk @katsuhitosudoh @MarineCarpuat
Meet the FBK MT group at #INTERSPEECH2024 next week! ๐ฌ๐ท
Our @beomseok_lee_ will attend the conference and present the following paper!
More info is available on our website: https://mt.fbk.eu/1-paper-accepted-at-interspeech-2024/
#INTERSPEECH2024 #SPEECH #SLU
Our pick of the week by @mgaido91: "MaLA-500: Massive Language Adaptation of Large Language Models" by @lpq29743, @shaoxiongji, @TiedemannJoerg, @andre_t_martins and @HinrichSchuetze.
#NLProc #LLM #multilingual #language #adaptation