New test reveals AI still lacks common sense

New test reveals AI still lacks common sense

Natural language processing (NLP) has taken great strides recently—but how much does AI understand of what it reads? Less than we thought, according to researchers at USC's Department of Computer Science. In a recent paper Assistant Professor Xiang Ren and Ph.D. student Yuchen Lin found that despite advances, AI still doesn't have the common sense needed to generate plausible sentences.

10 mentions: @MargaretSiegien@ChiSquatch@CapgeminiIndia@yoquankara
Date: 2020/11/20 06:52

Referring Tweets

@yoquankara 最新言語モデルでもまだ常識的な理解ができていない t.co/L9cOmCVYHk t.co/NjqtukwKwW
@CapgeminiIndia Current machine text-generation models can write an article that may be convincing to many humans, but they're basically mimicking what they have seen in the training phase. t.co/gdJdjkLhqb #LatestInTech

Related Entries

Read more [1906.09777] A Tensorized Transformer for Language Modeling
0 users, 1 mentions 2019/08/14 05:16
Read more Weights & Biases
0 users, 5 mentions 2020/06/02 20:21
Read more W&B Deep Learning Salon - Dylan Paiton & Andrew Ferlitsch - YouTube
0 users, 4 mentions 2020/09/03 23:22
Read more Webinar Registration - Zoom
0 users, 4 mentions 2020/09/14 23:22
Read more W&B Deep Learning Salon - Chirag Agarwal & Charles Frye - YouTube
0 users, 4 mentions 2020/11/11 03:51