MateCat worked at a new frontier of Computer Assisted Translation (CAT) technology, that is, how to effectively and ergonomically integrate Machine Translation (MT) within the human translation workflow. At a time in which MT was mainly trained with the objective of creating the most comprehensible output, MateCat targeted the development of MT technology aimed at minimizing the translator’s post-edit effort. To this end, MateCat developed an enhanced web-based CAT tool offering new MT capabilities, such as automatic adaption to the translated content, online learning from user corrections, and automatic quality estimation.
Our pick of the week by @lina_conti: "Exploring NMT Explainability for Translators Using NMT Visualising Tools" by Gonzalez-Saez, @MariamNakhle, @MeLlamoJamesT, @raheel_qader, @didier_schwab, et al., 2024.
#NMT #NLP #NLProc #explainiableAI #XAI
Our pick of the week by @beomseok_lee_: "DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding" by Shon, @shinjiw_at_cmu, et al., 2024.
#SLU #speech #LLM
Our pick of the week by @BeatriceSavoldi: "Rethinking Model Evaluation as Narrowing the Socio-Technical Gap" by @QVeraLiao and @ZiangXiao, 2023.
#Human #HumanCentered #Model #Evaluation #ModelEvaluation #AI
📢Come and join our group!
We offer a fully funded 3-year PhD position with the IECS Doctorate School @UniTrento:
Speech Translation in the LLM Era (Area A6)
⏱️Deadline: August 5th, 2024, h 4.00pm (CEST)
đź“ŚApplication Details: https://iecs.unitn.it/education/admission/call-for-application
#NLProc @FBK_research