Cross-Lingual Transfer Learning with DeepMind
Sebastian Ruder, a Research Scientist at DeepMind, joined us at the Conversational AI & NLP Virtual Summit in April 2021:
Research in natural language processing (NLP) has seen striking advances in recent years, mainly driven by large pre-trained language models. However, most of these successes have been achieved in English and a small set of other high-resource languages. In this talk, I will highlight methods that enable us to scale NLP models to more of the world's 7,000 languages, challenges, and promising future directions.
Key takeaways:
- Multilingual models are necessary in order to democratise access to language technology.
- Large language models trained on unlabelled data in many languages learn a surprising amount of cross-lingual information.
- Nevertheless, there are many open challenges such as generalisation to languages with limited data.
Видео Cross-Lingual Transfer Learning with DeepMind канала RE•WORK
Research in natural language processing (NLP) has seen striking advances in recent years, mainly driven by large pre-trained language models. However, most of these successes have been achieved in English and a small set of other high-resource languages. In this talk, I will highlight methods that enable us to scale NLP models to more of the world's 7,000 languages, challenges, and promising future directions.
Key takeaways:
- Multilingual models are necessary in order to democratise access to language technology.
- Large language models trained on unlabelled data in many languages learn a surprising amount of cross-lingual information.
- Nevertheless, there are many open challenges such as generalisation to languages with limited data.
Видео Cross-Lingual Transfer Learning with DeepMind канала RE•WORK
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Eugenio Culurciello, Founder, TeraDeep - RE.WORK Deep Learning Summit 2015Interview with Adam Cheyer, Co-Founder and VP Engineering/VP of R&D at Viv Labs/SamsungIn Search of Trustworthy & Ethical AI | Women in AI Podcast | Rachel Alexander, Omina TechnologiesChallenges of Human Labour Automatization in Transport - Juris Puce - Deep Learning Summit #reworkDLSuperior Conversational Customer Experience for the Enterprise with RasaML Observability: A Critical Piece in Ensuring Responsible AI | Arize AITraining Models at Facebook Scale with PyTorchInterview with Jeff Stein, Orbital Insight - RE•WORK Connect Summit #reworkAIHow Motion-Based, Off-Grid Renewable Energy Will Power the IoT - Jessica O. Matthews, Uncharted PlayThis week is the Deep Learning Summit & Deep Learning in Healthcare Summit BostonWearables: Moving Beyond Sensing - Sonny Vu, CEO, Misfit Wearables7-Eleven Using Applied AI to Disrupt Convenience - Shahmeer Mirza, 7ElevenInterview With Jeremy Marvel, National Institute of Standards and TechnologyElaine Warburton, QuantuMDx - RE.WORK & #BehindTheFaceRainer Sternfeld, Founder & CEO, Planet OS - IOT Summit, London 2015The RE.WORK IoT Summit, London, 2015Rob May, CEO, Talla - RE•WORK Virtual Assistant Summit, San Francisco 2016 #reworkAIAutomating Data Annotation with MicroModels with SamaHow Magical Technology will Revolutionize Human Health - Juhan Sonin, Involution StudiosIoT Summit, Boston 2015 - with MIT, Xively, INEX Advisors, SafeLogic & more #reworkconnectGrowing the Intelligence of Future City Infrastructure, Eric Yeatman, Imperial