Published Jun 8, 2018
58 - Learning What’s Easy: Fully Differentiable Neural Easy-First Taggers, with André Martins
Explore the groundbreaking work of André Martins as he delves into the use of constrained softmax and easy-first decoding in neural taggers, uncovering their potential to revolutionize part-of-speech and named entity recognition with enhanced efficiency and accuracy.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
44 - Truly Low Resource NLP, with Anders Søgaard
Answers 383 questions
29 - Neural machine translation via binary code prediction, with Graham Neubig
Answers 383 questions
63 - Neural Lattice Language Models, with Jacob Buckman
Answers 383 questions25 - Neural Semantic Parsing over Multiple Knowledge-bases
Answers 383 questions
56 - Deep contextualized word representations, with Matthew Peters
Answers 383 questions
114 - Behavioral Testing of NLP Models, with Marco Tulio Ribeiro
Answers 383 questions
117 - Interpreting NLP Model Predictions, with Sameer Singh
Answers 383 questions
109 - What Does Your Model Know About Language, with Ellie Pavlick
Answers 383 questions
19 - End-to-end Differentiable Proving, with Tim Rocktäschel
Answers 383 questions
34 - Translating Neuralese, with Jacob Andreas
Answers 383 questions
64 - Neural Network Models for Sentence Pair Tasks, with Wuwei Lan and Wei Xu
Answers 383 questions20 - A simple neural network module for relational reasoning
Answers 383 questions
