{"id":361,"date":"2014-07-11T02:36:57","date_gmt":"2014-07-11T02:36:57","guid":{"rendered":"http:\/\/ec2-52-79-86-100.ap-northeast-2.compute.amazonaws.com\/?p=361"},"modified":"2024-05-01T14:45:06","modified_gmt":"2024-05-01T05:45:06","slug":"architecture-and-adaptive-machinery-for-human-computer-conversation-seminar","status":"publish","type":"post","link":"https:\/\/blog.themusio.com\/?p=361","title":{"rendered":"Architecture and Adaptive Machinery for Human-Computer Conversation seminar"},"content":{"rendered":"<p><a href=\"http:\/\/akaon.com\/blog\/wp-content\/uploads\/2014\/07\/A-Computational-Architecture-for-Conversation_AKAStudy_071114.pdf\" target=\"_blank\" rel=\"noopener\">A Computational Architecture for Conversation_AKAStudy<\/a><\/p>\n<p><em>Andy made a presentation on this seminar and the introduction to this is as follows:<\/em><\/p>\n<p>&nbsp;<\/p>\n<p>***Peeking Into The Seminar***<\/p>\n<p>&nbsp;<\/p>\n<p>This seminar was to study dissertations on inference methods and structuring that make human-computer interaction possible. This is about two dissertations from professor Eric Horvitz, a researcher\u00a0at\u00a0Microsoft,\u00a0a\u00a0leading company in computer conversation, and professor Tim Paek from Stanford.\u00a0The first paper is about research on the\u00a0Bayesian Receptionist, which\u00a0functions through\u00a0the front desk of\u00a0the Microsoft\u00a0Seattle office. It is based on\u00a0the\u00a0Bayesian Network which uses Bayesian Inference\u00a0which\u00a0utilizes information other than just statistical sampling.\u00a0It\u00a0makes\u00a0inferences by\u00a0transferring its\u00a0way of understanding the purpose\u00a0of\u00a0the\u00a0conversation into a structure with 3 layers.\u00a0For example, if the Bayesian Receptionist judges that the user\u2019s purpose is to find a shuttle bus, it automatically identifies whether he is alone or in a group\u00a0and\u00a0which way the bus is going. Additionally, it works on continuing the conversation asking whether the user needs a VIP or handicapped\u00a0seat. Concepts that are used here are Natural Language Processing, Value of Information, and\u00a0Decision-theoretic Control other than just Bayesian inference.\u00a0The second paper contains the analysis on linguistic and visual information, and the errors occurring in the conversational channels and signals. It also includes strategies to control the whole conversation, make corrections automatically,\u00a0manage\u00a0possible threats.\u00a0It has been a task for machine learning to analyze the conversation and\u00a0compile\u00a0it into a structure that computers can understand. It might\u00a0require\u00a0a lot of research not only in the field\u00a0of\u00a0computer science, but also in the field of psychology and statistics to\u00a0predict\u00a0where the conversation is going on and the cost\u00a0of\u00a0analyzing these, etc.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>A Computational Architecture for Conversation_AKAStudy Andy made a presentation on this seminar and the introd [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_exactmetrics_skip_tracking":false,"_exactmetrics_sitenote_active":false,"_exactmetrics_sitenote_note":"","_exactmetrics_sitenote_category":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[3642,3640],"tags":[4598,4600,3656,4526,4360,4602,4364,4608,4604,4610,4554,3990,4606],"class_list":["post-361","post","type-post","status-publish","format-standard","hentry","category-ai-en","category-all-en","tag-adaptive-machinery-en","tag-architecture-en","tag-baggage-en","tag-bayesian-inference-en","tag-decision-theoretic-control-en","tag-human-computer-conversation-en","tag-linguistics-en","tag-listening-en","tag-live-en","tag-loebner-test-en","tag-long-short-term-memory-en","tag-lower-bound-en","tag-natural-language-en"],"aioseo_notices":[],"jetpack_sharing_enabled":true,"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/blog.themusio.com\/index.php?rest_route=\/wp\/v2\/posts\/361","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.themusio.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.themusio.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.themusio.com\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.themusio.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=361"}],"version-history":[{"count":3,"href":"https:\/\/blog.themusio.com\/index.php?rest_route=\/wp\/v2\/posts\/361\/revisions"}],"predecessor-version":[{"id":10943,"href":"https:\/\/blog.themusio.com\/index.php?rest_route=\/wp\/v2\/posts\/361\/revisions\/10943"}],"wp:attachment":[{"href":"https:\/\/blog.themusio.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=361"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.themusio.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=361"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.themusio.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=361"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}