Within the project, we are involved in “Spoke 2 – Integrative AI” which aims to provide theoretical and experimental evidence of the advantages of Integrative AI.Read More
The PF-STAR project intended to contribute to establish future activities in the field of multisensorial and multilingual communication (interface technologies) on firmer bases by providing technological baselines, comparative evaluations, and assessment of prospects of core technologies, which future research and development efforts can build from.Read More
The project concentrated on the access to information contained in very large, unstructured, heterogeneous repositories, on multimodal presentation of information, and on the assessment of the quality of information.Read More
FLaReNet aims at developing a common vision of the area and fostering a European strategy for consolidating of Language Resources and Language Technologies, thus enhancing competitiveness at EU level and worldwide.Read More
Ontotext exploits text processing and automatic reasoning technologies based on the philosophy of the Semantic Web to extract knowledge from texts and to organise it conceptually in an ontology.Read More
JUMAS addresses the need to build an infrastructure able to optimise the information workflow in order to facilitate later analysis.Read More
PATExpert developed a multimedia content representation formalism based on Semantic Web technologies for selected technology areas and investigate the retrieval, classification, multilingual generation of concise patent information, assessment and visualization of patent material encoded in this formalism, taking the information needs of all user types as defined in a user typology into account.Read More
NESPOLE! System has been developed using two scenarios: the tourism scenario and the first aid medical assistance scenario.Read More
A project aimed at automating the dynamic multilingual synchronization process of Wikis.Read More
FAME addressed the problem of integrating multiple communications modalities blending the physical and virtual worlds to provide support for multicultural communication and problem solving.Read More
PESCaDO offered an interconnected multipurpose environmental user-oriented service for a federated community of citizens, public services (such as tourist offices and environmental institutions), public administrations, and entrepreneurs active in sectors sensitive to environmental conditions.Read More
MateCat pushed the new frontier of Computer Assisted Translation (CAT) technology: how to effectively integrate machine translation within the human translation workflow.Read More
The main concept of the project EuroSentiment was to provide a shared language resource pool for fostering sentiment analysis.Read More
META-NET is a Network of Excellence dedicated to fostering the technological foundations of a multilingual European information societyRead More
The general objective of QALL-ME was to establish a shared infrastructure for multilingual and multimodal open domain Question Answering for mobile phones.Read More
EU-BRIDGE aims at developing automatic transcription and translation technology that will permit the development of innovative multimedia captioning and translation services of audiovisual documents between European and non-European languages.Read More
CRACKER (Cracking the Language Barrier: Coordination, Evaluation and Resources for European MT Research)
CRACKER is a Machine Translation (MT) research initiative involving 7 major universities and research institutions.Read More
1 February 2005 to 31 January 2018
QT21 is a European research and innovation initiative to develop improved machine translation models for challenging languages and scenarios, focusing on scalability and minimizing reliance on data, while incorporating continuous learning and evaluation guided by human translators.Read More
‼️ *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)
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