The Machine Translation (MT) research unit of the Digital Industry Center pursues research in the field of automatic translation, both from text and speech, and develops technology to enable multilingual communication and access to large-scale spoken and written content. The unit’s core activities include the creation of innovative neural architectures and the development of methods to adapt them to different contexts, domains and application scenarios (e.g. subtitling, dubbing, and interpreting). The unit has also an active strand of research on the analysis and mitigation of gender bias in automatic translation. Besides its long record of scientific results, the MT unit has a well-recognized role in the creation and release of language resources and in the organization of international evaluation campaigns on MT-related tasks.
‼️ *Paper, code, models, and outputs out* for one of our last papers "AlignAtt" about Simultaneous Speech Translation recently published at #Interspeech2023!
📍Official Paper: https://www.isca-speech.org/archive/pdfs/interspeech_2023/papi23_interspeech.pdf
📍Repo (code, etc.): https://github.com/hlt-mt/FBK-fairseq/blob/master/fbk_works/ALIGNATT_SIMULST_AGENT_INTERSPEECH2023.md
#NLProc #NLP #speech #translation
Our pick of the week by @apierg: "Prompt-Driven Neural Machine Translation" by Li et al., Findings ACL 2022.
#machine #translation #MT #NLP #NLProc #ACL #computational #linguistics #prompt
The call for diversity and inclusion (D&I) subsidies for #EMNLP2023 is online!
EMNLP 2023 is providing D&I funds for registration, caregiving, bandwidth, travel and VPN subsidies.
Deadline: October 20, 2023 11:59pm (Anywhere on Earth)
Details:
#NLProc
One of the very first multilingual and multimodal model to obtain performance competitive with dedicated models, maybe the first of many? Anyway, a very interesting read: https://arxiv.org/pdf/2308.11466.pdf