WIKINSIGHTS.ORG

exensa.com

About Us | eXenSa

http://www.exensa.com/about-us

Bring your data to life. At this point, I could not return to symbolic approaches. After a couple of years, I made a major discovery. I must admit that I discovered the basics of the NCISC algorithm mostly by chance. And luckily, this discovery happened precisely after I left my last postdoc position at the CEA, with Gregory Grefenstette. The best advisor of my short career in academics. That's how the story begins. I'm sure you will be want to help us write the rest of it. We sell licences and customiza...

blog.guillaume-pitel.fr

eXenSa / Pivot / eXenGine

http://blog.guillaume-pitel.fr/2014/04/exensa-pivot-exengine

Adventure in collaborative filtering, information retrieval, matrix factorization and other stuff. EXenSa / Pivot / eXenGine. I just realized that I haven’t posted a single word about the fate of our SalesAdviser product (SaaS recommendations for e-commerce). I’ve had this project to publish a video of me explaining why we failed at it, but I think I won’t have time to devote to this before long. So let’s write it here. A Business Model that seemed to hurt our customers feelings : one of the great ideas ...

uebercomputing.com

Wikipedia Processing Using Spark

http://uebercomputing.com/scala/2014/11/19/Wikipedia-Processing-Using-Spark

Incremental Scala compilation with Zinc. Scala SDK 4.0 RC2. Wikipedia Processing Using Spark. How this investigation started. As a subscriber to the user/dev@spark.apache.org mailing lists I try to keep up with the activity on the list. When I find something interesting I usually just archive the email message. But this email thread and subsequent investigation sparked my interest and so I wanted to capture the info and some of the subsequent processing details. Spark Dev message 03520. Which was also li...

iswag-symposium.org

iSWAG Symposium 2015

http://iswag-symposium.org/2015

The International Symposium on Web Algorithms (iSWAG) is dedicated to all academic and industrial researchers working on algorithmic problems related to the web. The aim of iSWAG 2015 is to cover as completely as possible the field of research on algorithms for solving web related problems. We sincerely thank our sponsors for supporting our mission and making the symposium possible! Qwant is a search engine that respects your privacy and facilitates the discovery and sharing through social approach.

blog.guillaume-pitel.fr

eXenSa

http://blog.guillaume-pitel.fr/category/exensa

Adventure in collaborative filtering, information retrieval, matrix factorization and other stuff. Does SGNS (Word2Vec) encodes word frequency? I’ve been wondering for a while about the behaviour of SGNS vs SVD/PMI with regards to the difference of performance on analogy questions. (Have a look at Omer Levy’s TACL article. For a deep comparison of different methods). One of the thing that made me think that SGNS could encode frequency is when I look at the neighbours of rare words :. X the query count.

blog.guillaume-pitel.fr

avril 2014

http://blog.guillaume-pitel.fr/2014/04

Adventure in collaborative filtering, information retrieval, matrix factorization and other stuff. Amazing results of NCISC on Netflix. Last week, I’ve played a little bit with the Netflix prize dataset and NC-ISC. The results are amazingly better than the current state of the art. Over the current state of the art. This is a huge gain. And it could be applied to other recommendation problems. Music, jobs,. In e-commerce and social shopping, etc. A bit of context. Was an open competition held in 2009&#46...

blog.guillaume-pitel.fr

Mostly linguistically computational | Adventure in collaborative filtering, information retrieval, matrix factorization and other stuff | Page 2

http://blog.guillaume-pitel.fr/page/2

Adventure in collaborative filtering, information retrieval, matrix factorization and other stuff. Paris Datageeks talk : video available. I gave a talk at the Paris Datageeks meetup a month ago. Here is the video. Of my presentation of Apache Spark. Amazing results of NCISC on Netflix. Last week, I’ve played a little bit with the Netflix prize dataset and NC-ISC. The results are amazingly better than the current state of the art. Over the current state of the art. This is a huge gain. Music, jobs,.

blog.guillaume-pitel.fr

Mostly linguistically computational | Adventure in collaborative filtering, information retrieval, matrix factorization and other stuff | Page 4

http://blog.guillaume-pitel.fr/page/4

Adventure in collaborative filtering, information retrieval, matrix factorization and other stuff. Diaspora the distributed social networking system. After I wrote my last post, I immediately thought “Darn, I’ve forgotten to talk about Diaspora”. Fortunately, nobody has flamed me yet…. Posted in: social networking. Standard protocol for Social Networking. I’m not the only one to think that way, of course : Adrian Thurston. Has developped the distributed social networking protocol. It would probably not e...