Richard Socher: One of the hardest problems in #AI is common sense reasoning. This paper by @nazneenrajani, @BMarcusMcCann, @CaimingXiong+I makes huge progress on this. Powerful, simple and unsupervised method: https://arxiv.org/abs/1906.02361
Blog: https://blog.einstein.ai/leveraging-language-models-for-commonsense/ https://t.co/lolDykY8Wt
7 replies, 684 likes
Miles Brundage: "Explain Yourself! Leveraging Language Models for Commonsense Reasoning," Rajani et al.: https://arxiv.org/abs/1906.02361
0 replies, 18 likes
arxiv: Explain Yourself! Leveraging Language Models for Commonsense Reasoning. http://arxiv.org/abs/1906.02361 https://t.co/lOCnFa5PNG
0 replies, 14 likes
Vinod Khosla: Far from enough but a start to common sense reasoning: https://arxiv.org/pdf/1906.02361.pdf ; where will a dozen different attempts lead from DL to Bayesian, graph,...?
0 replies, 13 likes
Salesforce Research: Can neural networks use auto-generated reasoning?
Today, at @ACL2019_Italy, we had a session on leveraging language models for commonsense reasoning from our very own @nazneenrajani !
Check out the paper below: https://arxiv.org/abs/1906.02361 https://t.co/YNOlVF3UHm
0 replies, 10 likes
Susanna @ Indigenous.Engineering: i'm fascinated by this paper. applying language models to improve common sense reasoning in deep neural networks by training the model on human-generated answers to questions...until it can infer its own. so COOL
#NLProc #DataScience #MachineLearning
0 replies, 3 likes
Nazneen Rajani ✈️ ACL2019 Italy: I will be presenting this work today in Hall 4 at 2:50pm. If you are interested in explainable AI (XAI) or commonsense reasoning, don't miss this! #acl2019nlp
1 replies, 3 likes
Kiran Kannar: brilliant talk by @nazneenrajani on Xplainable AI. highly recommend the associated paper https://arxiv.org/abs/1906.02361
0 replies, 1 likes
Hima Lakkaraju: This looks very interesting @RichardSocher.
0 replies, 1 likes
Found on Jul 02 2019 at https://arxiv.org/pdf/1906.02361.pdf