#TATAELXSI Weekly chart indicates we're near top as continuous profit booking . https://t.co/p5b5cYVtRP

Can we control the output of neural generation systems?
Can we build a better chatbot using this control?
And what makes a good conversation anyway?

Check out the blog post for our NAACL paper:

https://t.co/UAAUxSeA0L

#AI #NLProc #DeepLearning #ConversationalAI @facebookai

This post got a little delayed since the paper's publication, but the intervening time has given me an opportunity to reflect.

So this post has some extra thoughts regarding more recent NLG developments - e.g., pretrained models like GPT(2), and the suitability of beam search.

Thread: *Post-Liberal reading list*
1/ Religion and the Rise of Capitalism - R.H. Tawney
Unto This Last - John Ruskin
Liberty, Equality, Fraternity - James Fitzjames Stephen
The Great Transformation - Karl Polanyi
The Quest for Community - Robert Nisbet

2/ Family and Civilisation - Carle C. Zimmerman
Science, Politics and Gnosticism - Eric Voegelin
Liberty Before Liberalism - Quentin Skinner
The Great Debate - Yuval Levin
Lincoln and the Politics of Christian Love - Grant Havers
Where We Are - Roger Scruton

3/ The Humane Vision of Wendell Berry - Various
The Unsettling of America - Wendell Berry
Moral Matters - Mark Dooley
Red Tory - Phillip Blond
Blue Labour - Eds. Ian Geary and Adrian Pabst
Together for the Common Good - Eds. Nicholas Sagovsky & Peter McGrail

4/ The Politics of Virtue - John Milbank & Adrian Pabst
Localism in a Mass Age - Eds. Mark T. Mitchell & Jason Peters
The Antimodern Condition - Peter King
The Principle of Duty - David Selbourne
Nostalgia - Anthony Esolen
A Common Human Ground - Claes G. Ryn

5/ The Politics of Gratitude - Mark T. Mitchell
A Time to Build - Yuval Levin
Remaking One Nation - Nick Timothy
Despised - Paul Embery
Defending Identity - Natan Sharansky
Between Kin and Cosmopolis - Nigel Biggar
The Virtue of Nationalism - Yoram Hazony

Thirumalai Murugan Kovil
#Panpoli
#TamilNaduTemples 🚩

Thirumalai Murugan Temple is located in Tenkasi district of Tamil Nadu. Muruga is worshipped as Thirumalai kumarasamy. Temple is situated near Kerala border and known to be where Shri Murugan gave darshan to Rishi Agasthiar

Devi is worshipped in the temple as Thirumalai Kaali amman

Sthala Puranam says that, there was a priest named Poovanbhattar of Thirumalai Kaali amman. Murugar appeared in a dream of the bhattar and said to find a Vigraham, lying in particular place which is of Thirumalaikumaran

Bhattar conveyed the news to the Pandalam Raja and they went to find out the vigraham. Surprisingly ants showed the way to find the Vigraham. Thus Murugan vigraham was found and Prathista was done here. There is a lake with pure water on the top of the hill

which is said to be created by Agasthiyar. It is believed that kannaki of
Chilapathikaram visited here before going to Kerala. Sapthamathrukkal also worshipped Murugan here. Kanthashashti Thiruvizha is very famous here.

Om Muruga
Muruganukku Harohara
🙏🕉🙏

1 There's a chasm between an NLP technology that works well in the research lab and something that works for applications that real people use. This was eye-opening when I started my career, and every time I talk to an NLP engineer at @textio, it continues to strike me even now.

2 Research conditions are theoretical and/or idealized. A huge problem for so-called NLP or AI startups with highly credentialed academic founders is that they bring limited knowledge of what it takes to build real products outside the lab.

3 A product is ultimately a thing that people pay for - not just cool technology or user experience. But I’m not even talking about knowledge gaps in go-to-market work. I'm talking purely technical gaps: how you go from science project to performant + delightful user experience.

4 Most commoditized NLP packages solve well-understood problems in standard ways that sacrifice either precision or performance. In a research lab, this is not usually a hard trade-off; in general, no one is using what you make, so performance is less important than precision.

5 In software, when you’re making something for real people to use, these tradeoffs are a big deal. Especially if you’re asking those people to pay for what you’ve made (can’t get away from that pesky GTM thinking). They expect quality, which includes precision AND performance.