Published May 4, 2021
125 - VQA for Real Users, with Danna Gurari
Discover the groundbreaking advancements in Visual Question Answering (VQA) for blind users as Danna Gurari unveils innovative algorithms and the pivotal role of industry collaboration, highlighted by the creation of the Vizwiz dataset to tackle real-world data challenges.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
13 - Question Answering from Unstructured Text by Retrieval and Comprehension
Answers 383 questions
96 - Question Answering as an Annotation Format, with Luke Zettlemoyer
Answers 383 questions
82 - Visual Reasoning, with Yoav Artzi
Answers 383 questions
38 - A Corpus of Natural Language for Visual Reasoning, with Alane Suhr
Answers 383 questions
108 - Data-To-Text Generation, with Verena Rieser and Ondřej Dušek
Answers 383 questions03 - FastQA: A Simple and Efficient Neural Architecture for Question Answering
Answers 383 questions
105 - Question Generation, with Sudha Rao
Answers 383 questions30 - Probabilistic Typology: Deep Generative Models of Vowel Inventories
Answers 383 questions28 - Data Programming: Creating Large Training Sets, Quickly
Answers 383 questions09 - Learning to Generate Reviews and Discovering Sentiment
Answers 383 questions02 - Bidirectional Attention Flow for Machine Comprehension
Answers 383 questions
72 - The Anatomy Question Answering Task, with Jordan Boyd-Graber
Answers 383 questions
128 - Dynamic Benchmarking, with Douwe Kiela
Answers 383 questions25 - Neural Semantic Parsing over Multiple Knowledge-bases
Answers 383 questions
