Published Oct 17, 2017
34 - Translating Neuralese, with Jacob Andreas
Jacob Andreas demystifies 'neuralese' by exploring cutting-edge techniques for translating the language of neural networks, highlighting the role of grounding and the challenges of interpreting data-less communication while envisioning future applications in AI and multi-agent interactions.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
63 - Neural Lattice Language Models, with Jacob Buckman
Answers 383 questions
29 - Neural machine translation via binary code prediction, with Graham Neubig
Answers 383 questions
44 - Truly Low Resource NLP, with Anders Søgaard
Answers 383 questions25 - Neural Semantic Parsing over Multiple Knowledge-bases
Answers 383 questions
61 - Neural Text Generation in Stories, with Elizabeth Clark and Yangfeng Ji
Answers 383 questions
121 - Language and the Brain, with Alona Fyshe
Answers 383 questions
81 - BlackboxNLP, with Afra Alishahi and Tal Linzen
Answers 383 questions
54 - Simulating Action Dynamics with Neural Process Networks, with Antoine Bosselut
Answers 383 questions
91 - (Executable) Semantic Parsing, with Jonathan Berant
Answers 383 questions
38 - A Corpus of Natural Language for Visual Reasoning, with Alane Suhr
Answers 383 questions
69 - Second language acquisition modeling, with Burr Settles
Answers 383 questions
