Published May 12, 2017
04 - Recurrent Neural Network Grammars, with Chris Dyer
Chris Dyer delves into parsing techniques with a focus on top-down parsing, tree structure generation, and the advantages of generative models over discriminative ones, elucidating how these approaches enhance linguistic theories and natural language processing efficiency.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
10 - A Syntactic Neural Model for General-Purpose Code Generation
Answers 383 questions
29 - Neural machine translation via binary code prediction, with Graham Neubig
Answers 383 questions05 - Transition-Based Dependency Parsing with Stack Long Short-Term Memory
Answers 383 questions
61 - Neural Text Generation in Stories, with Elizabeth Clark and Yangfeng Ji
Answers 383 questions09 - Learning to Generate Reviews and Discovering Sentiment
Answers 383 questions25 - Neural Semantic Parsing over Multiple Knowledge-bases
Answers 383 questions
63 - Neural Lattice Language Models, with Jacob Buckman
Answers 383 questions
15 - Attention and Augmented Recurrent Neural Networks
Answers 383 questions
22 - Deep Multitask Learning for Semantic Dependency Parsing, with Noah Smith
Answers 383 questions30 - Probabilistic Typology: Deep Generative Models of Vowel Inventories
Answers 383 questions
108 - Data-To-Text Generation, with Verena Rieser and OndrÌŒej DusÌŒek
Answers 383 questions
138 - Compositional Generalization in Neural Networks, with Najoung Kim
Answers 383 questions
