CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge

06-14

From Recognition to Cognition: Visual Commonsense Reasoning

06-14

ERNIE: Enhanced Language Representation with Informative Entities

06-14

Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions

04-03

Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog

04-01

Image-Question-Answer Synergistic Network for Visual Dialog

04-01

DRr-Net: Dynamic Re-read Network for Sentence Semantic Matching

03-20

Image-Enhanced Multi-Level Sentence Representation Net for Natural Language Inference

03-19

Neural Network for Named Entity Typing方法总结

07-04

What Value Do Explicit High Level Concepts Have in Vision to Language Problems?

06-30