Machine Translation Insights
Parinaz discusses the evolution of machine translation, highlighting the shift towards byte pair encodings that utilize subwords lacking inherent meaning. This change raises questions about the interpretability of model decisions, particularly in relation to deep learning's empirical nature. The conversation delves into whether this trend can be reversed and what it means for the future of AI.In this clip
From this podcast
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Live from TWIMLcon! Operationalizing Responsible AI - #310
Related Questions
How do advancements in AI, as discussed in the episode Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94 and the clip Surprising Success of GPT-2, influence the field of translation?
What does Ilya Sutskever think about the understanding of language by models like GPT-2 in the episode Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94 and the clip Surprising Success of GPT-2?
What does Ilya Sutskever think about the understanding of language by models like GPT-2 in the episode Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94 and the clip Language and Learning?