Jul 11, 2020The missing pieces in virtual-ACLSo, ACL 2020, the first all-virtual major NLP event, is now over. It was intense, it was informative, we learned many things (see a nice summary by Vered here), we are exhausted like after previous ACL conferences, if not more. …10 min read
Published in AI2 Blog·Apr 27, 2020SPIKE-CORD: Powerful search over CORD-19To leverage the important CORD-19 resource released in March by AI2’s Semantic Scholar team and several partners, our team at AI2 Israel is launching SPIKE-CORD, a powerful set of tools for effectively searching and interacting with the CORD-19 data. Using a family of three query languages, SPIKE-CORD exposes a host…NLP7 min read
Jun 10, 2017A Response to Yann LeCun’s Response.I appreciate the interest and debate around my post, and Yann’s response on facebook. Let me respond to the response. [I chose to have it here and not on facebook, because, while I have an old an inactive facebook account, I rather not use it. I already spend tons of…Machine Learning5 min read
Jun 9, 2017Clarifications re “Adversarial Review of Adversarial Learning of Nat Lang” postWow. That piece about the bad adversarial NLG paper really struck a nerve. Its been getting tons of attention, and some very positive comments. Thanks! There are also a few points that people (especially, I think, younger researchers) raise, either on the web or in private, along the lines of…Machine Learning4 min read
Jun 9, 2017An Adversarial Review of “Adversarial Generation of Natural Language”Or, for fucks sake, DL people, leave language alone and stop saying you solve it. [edit: some people commented that they don’t like the us-vs-them tone and that “deep learning people” can — and some indeed do — do good NLP work. To be clear: I fully agree. #NotAllDeepLearners ] [update: I added some clarifications based on responses to this piece. I suggest reading them…Machine Learning14 min read