{"id":215005,"date":"2016-02-02T13:29:27","date_gmt":"2016-02-02T13:29:27","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/learning-with-n-grams-from-massive-scales-to-compressed-representations\/"},"modified":"2016-08-16T14:23:16","modified_gmt":"2016-08-16T21:23:16","slug":"learning-with-n-grams-from-massive-scales-to-compressed-representations","status":"publish","type":"msr-video","link":"https:\/\/www.microsoft.com\/en-us\/research\/video\/learning-with-n-grams-from-massive-scales-to-compressed-representations\/","title":{"rendered":"Learning with N-Grams: From Massive Scales to Compressed Representations"},"content":{"rendered":"<div class=\"asset-content\">\n<p>N-gram models are essential in any kind of text processing; they offer simple baselines that are surprisingly competitive with more complicated &#8220;state of the art&#8221; techniques. I will present a survey of my work for learning with arbitrarily long N-grams at massive scales. This framework combines fast matrix multiplication with a dual learning paradigm that I am developing to reconcile sparsity-inducing penalties with Kernels. The presentation will focus on Dracula, a new form of deep learning based on classical ideas from compression. Dracula is a combinatorial optimization problem, and I will discuss some its problem structure and use this to visualize its solution surface.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>N-gram models are essential in any kind of text processing; they offer simple baselines that are surprisingly competitive with more complicated &#8220;state of the art&#8221; techniques. I will present a survey of my work for learning with arbitrarily long N-grams at massive scales. This framework combines fast matrix multiplication with a dual learning paradigm that [&hellip;]<\/p>\n","protected":false},"featured_media":275583,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13556],"msr-video-type":[],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-215005","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/ykoQ8A3pVqo","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/215005"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":0,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/215005\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/275583"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=215005"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=215005"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=215005"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=215005"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=215005"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=215005"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}