{"id":438,"date":"2013-05-28T13:02:53","date_gmt":"2013-05-28T18:02:53","guid":{"rendered":"http:\/\/haleyai.com\/wordpress\/?p=438"},"modified":"2018-12-18T12:55:15","modified_gmt":"2018-12-18T17:55:15","slug":"background-for-our-semantic-technology-2013-presentation","status":"publish","type":"post","link":"http:\/\/haleyai.com\/wordpress\/2013\/05\/28\/background-for-our-semantic-technology-2013-presentation\/","title":{"rendered":"Background for our Semantic Technology 2013 presentation"},"content":{"rendered":"<p>In the spring of 2012, Vulcan engaged Automata for a knowledge acquisition (KA) experiment.\u00a0 This article provides background on the context of that experiment and what the results portend for artificial intelligence applications, especially in the areas of education.\u00a0 Vulcan presented some of the award-winning work referenced here at an AI conference, including a demonstration of the electronic textbook discussed below.\u00a0 There is a video of that presentation <a href=\"http:\/\/videolectures.net\/aaai2011_gunning_halobook\/\">here<\/a>.\u00a0 The introductory remarks are interesting but not pertinent to this article.<\/p>\n<h2>Background on Vulcan\u2019s Project Halo<\/h2>\n<p><a href=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/ProjectHaloFormation.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-large wp-image-440\" title=\"ProjectHaloFormation\" src=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/ProjectHaloFormation-1024x758.png\" alt=\"Background on Vulcan's Project Halo\" width=\"1024\" height=\"758\" srcset=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/ProjectHaloFormation-1024x758.png 1024w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/ProjectHaloFormation-300x222.png 300w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/ProjectHaloFormation.png 1317w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/a><\/p>\n<p>From 2002 to 2004, <a href=\"http:\/\/www.aaai.org\/ojs\/index.php\/aimagazine\/article\/view\/1783\/1681\">Vulcan developed a Halo Pilot that could correctly answer between 30% and 50% of the questions on advanced placement (AP) tests in chemistry<\/a>.\u00a0 The approaches relied on sophisticated approaches to formal knowledge representation and expert knowledge engineering.\u00a0 Of three teams, Cycorp fared the worst and SRI fared the best in this competition.\u00a0 SRI\u2019s system performed at the level of scoring a 3 on the AP, which corresponds to earning course credit at many universities.\u00a0 The consensus view at that time was that achieving a score of 4 on the AP was feasible with limited additional effort.\u00a0 However, the cost per page for this level of performance was roughly $10,000, which needed to be reduced significantly before Vulcan\u2019s objective of a Digital Aristotle could be considered viable.<\/p>\n<p><!--more--><\/p>\n<p><a href=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/AnsweringAdvancedPlacementQuestionsInScience.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-large wp-image-441\" title=\"AnsweringAdvancedPlacementQuestionsInScience\" src=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/AnsweringAdvancedPlacementQuestionsInScience-1024x732.png\" alt=\"Answering Advanced Placement Questions in Science\" width=\"1024\" height=\"732\" srcset=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/AnsweringAdvancedPlacementQuestionsInScience-1024x732.png 1024w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/AnsweringAdvancedPlacementQuestionsInScience-300x214.png 300w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/AnsweringAdvancedPlacementQuestionsInScience.png 1318w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/a><\/p>\n<h2>Background on Vulcan\u2019s Aura system<\/h2>\n<p>In 2004, Vulcan initiated phase II of Project Halo focused on enabling domain experts to develop systems capable of answering AP questions in chemistry, physics, and biology.\u00a0 The principal objective of this research was to determine the viability of reducing the cost of knowledge acquisition (KA) significantly while hopefully improving AP test performance.\u00a0 This resulted in <a href=\"http:\/\/www.ai.sri.com\/pubs\/files\/1545.pdf\">Vulcan\u2019s Aura system<\/a> during 2007.<\/p>\n<p><a href=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Vulcans-Advanced-User-centered-Reasoning-and-Acquisition-system-AURA.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-large wp-image-442\" title=\"Vulcan's Advanced User-centered Reasoning and Acquisition system (AURA)\" src=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Vulcans-Advanced-User-centered-Reasoning-and-Acquisition-system-AURA-1023x489.png\" alt=\"Vulcan's Advanced User-centered Reasoning and Acquisition system (AURA)\" width=\"1023\" height=\"489\" srcset=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Vulcans-Advanced-User-centered-Reasoning-and-Acquisition-system-AURA-1023x489.png 1023w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Vulcans-Advanced-User-centered-Reasoning-and-Acquisition-system-AURA-300x143.png 300w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Vulcans-Advanced-User-centered-Reasoning-and-Acquisition-system-AURA.png 1299w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/a><\/p>\n<p><a href=\"http:\/\/www.stanford.edu\/class\/cs227\/Readings\/20100121-aura-seminar.pdf\">Experiments conducted during 2008 and 2009 showed<\/a> that after two months of training and use of Aura, subject matter experts (SMEs) were able to encode knowledge sufficient to answer roughly 75% of AP questions in biology using Aura.<\/p>\n<p><a href=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Examples-of-Questions-that-Vulcans-AURA-can-answer.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-large wp-image-443\" title=\"Examples of Questions that Vulcan's AURA can answer\" src=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Examples-of-Questions-that-Vulcans-AURA-can-answer-1024x503.png\" alt=\"Examples of Questions that Vulcan's AURA can answer\" width=\"1024\" height=\"503\" srcset=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Examples-of-Questions-that-Vulcans-AURA-can-answer-1024x503.png 1024w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Examples-of-Questions-that-Vulcans-AURA-can-answer-300x147.png 300w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Examples-of-Questions-that-Vulcans-AURA-can-answer.png 1520w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/a><\/p>\n<p>The knowledge acquisition (KA) effort required was roughly 15 hours per page on average, whether by knowledge engineers (KEs) or SMEs.\u00a0 This level of performance came with caveats, however.\u00a0 First, questions had to be reformulated from natural language into a controlled syntax using precise terminology, which required several attempts and reformulations of questions by users.<\/p>\n<p><a href=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/The-Question-Answering-Cycle-in-Vulcans-AURA-and-Halobook-prototype-Inquire.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-large wp-image-444\" title=\"The Question Answering Cycle in Vulcan's AURA and Halobook prototype (Inquire)\" src=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/The-Question-Answering-Cycle-in-Vulcans-AURA-and-Halobook-prototype-Inquire-1024x767.png\" alt=\"The Question Answering Cycle in Vulcan's AURA and Halobook prototype (Inquire)\" width=\"1024\" height=\"767\" srcset=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/The-Question-Answering-Cycle-in-Vulcans-AURA-and-Halobook-prototype-Inquire-1024x767.png 1024w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/The-Question-Answering-Cycle-in-Vulcans-AURA-and-Halobook-prototype-Inquire-300x224.png 300w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/The-Question-Answering-Cycle-in-Vulcans-AURA-and-Halobook-prototype-Inquire.png 1591w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/a><\/p>\n<p>Second, certain limitations of Aura\u2019s knowledge representation and reasoning (KR&amp;R) limited performance below 80% correctness.\u00a0 <a href=\"http:\/\/silk.semwebcentral.org\/talk-silk-v22+addnal-typofix.pdf\">The latter weakness motivated Vulcan to begin developing SILK by 2008<\/a>.\u00a0 In particular, SILK targets the following areas:<\/p>\n<p><a href=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Areas-of-Brittleness-in-Vulcans-AURA-targeted-by-Vulcans-more-expressive-knowledge-representation-and-reasoning-system-SILK.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-445\" title=\"Areas of Brittleness in Vulcan's AURA targeted by Vulcan's more expressive knowledge representation and reasoning system (SILK)\" src=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Areas-of-Brittleness-in-Vulcans-AURA-targeted-by-Vulcans-more-expressive-knowledge-representation-and-reasoning-system-SILK.png\" alt=\"Areas of Brittleness in Vulcan's AURA targeted by Vulcan's more expressive knowledge representation and reasoning system (SILK)\" width=\"934\" height=\"697\" srcset=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Areas-of-Brittleness-in-Vulcans-AURA-targeted-by-Vulcans-more-expressive-knowledge-representation-and-reasoning-system-SILK.png 934w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Areas-of-Brittleness-in-Vulcans-AURA-targeted-by-Vulcans-more-expressive-knowledge-representation-and-reasoning-system-SILK-300x223.png 300w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/a><\/p>\n<p>While working towards more powerful KR&amp;R, Vulcan continued the experiment with Aura by focusing more broadly and deeply within the domain that raised the fewest immediate KR&amp;R challenges.\u00a0 Specifically, Vulcan scaled up the effort to cover all 59 chapters of <a href=\"http:\/\/www.pearsonschool.com\/index.cfm?locator=PS1294&amp;PMDbSiteId=2781&amp;PMDbSolutionId=6724&amp;PMDbSubSolutionId=&amp;PMDbCategoryId=811&amp;PMDbSubCategoryId=23496&amp;PMDbSubjectAreaId=&amp;PMDbProgramId=78581\">Campbell\u2019s Biology from Pearson<\/a>; roughly 30 times the 40 pages of knowledge acquired during the initial experiment.<\/p>\n<p><a href=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Phases-of-Vulcans-Project-Halo-from-Advanced-Placement-to-Syllabus-to-Textbook-from-knowledge-representation-experts-to-domain-experts-to-communities-of-scientists-and-teachers-in-education-and-research.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-large wp-image-446\" title=\"Phases of Vulcan's Project Halo from Advanced Placement to Syllabus to Textbook from knowledge representation experts to domain experts to communities of scientists and teachers in education and research\" src=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Phases-of-Vulcans-Project-Halo-from-Advanced-Placement-to-Syllabus-to-Textbook-from-knowledge-representation-experts-to-domain-experts-to-communities-of-scientists-and-teachers-in-education-and-research-1024x766.png\" alt=\"Phases of Vulcan's Project Halo from Advanced Placement to Syllabus to Textbook from knowledge representation experts to domain experts to communities of scientists and teachers in education and research\" width=\"1024\" height=\"766\" srcset=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Phases-of-Vulcans-Project-Halo-from-Advanced-Placement-to-Syllabus-to-Textbook-from-knowledge-representation-experts-to-domain-experts-to-communities-of-scientists-and-teachers-in-education-and-research-1024x766.png 1024w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Phases-of-Vulcans-Project-Halo-from-Advanced-Placement-to-Syllabus-to-Textbook-from-knowledge-representation-experts-to-domain-experts-to-communities-of-scientists-and-teachers-in-education-and-research-300x224.png 300w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Phases-of-Vulcans-Project-Halo-from-Advanced-Placement-to-Syllabus-to-Textbook-from-knowledge-representation-experts-to-domain-experts-to-communities-of-scientists-and-teachers-in-education-and-research.png 1306w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/a><\/p>\n<p>In parallel with scaling up coverage, Vulcan developed the concept of a HaloBook as discussed in Paul Allen\u2019s memoir, <a href=\"http:\/\/www.amazon.com\/Idea-Man-Memoir-Cofounder-Microsoft\/dp\/1591845378\">Idea Man<\/a>.\u00a0 In 2010, a prototype called Inquire was developed as an electronic textbook application for Apple\u2019s iPad.\u00a0 Inquire integrates questions and answers into the electronic textbook, enriching its content with conceptual structure and meaningful relationships using knowledge captured using Aura, effectively transforming a textbook in to a semantic platform for intelligent tutoring.<\/p>\n<p><a href=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Vulcans-concept-of-Halobook-an-intelligent-textbook.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-large wp-image-447\" title=\"Vulcan's concept of Halobook - an intelligent textbook\" src=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Vulcans-concept-of-Halobook-an-intelligent-textbook-1024x773.png\" alt=\"Vulcan's concept of Halobook - an intelligent textbook\" width=\"1024\" height=\"773\" srcset=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Vulcans-concept-of-Halobook-an-intelligent-textbook-1024x773.png 1024w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Vulcans-concept-of-Halobook-an-intelligent-textbook-300x226.png 300w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Vulcans-concept-of-Halobook-an-intelligent-textbook.png 1357w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/a><\/p>\n<p>The Inquire prototype avoids the issue of question (re)formulation discussed above by showing questions that appear to be related to the questions users ask.\u00a0 This approach avoids having to understand questions and provides users guidance concerning what they are asking about.<\/p>\n<p><a href=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Vulcans-Halobook-prototype-Inquire-answering-and-suggesting-questions.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-large wp-image-448\" title=\"Vulcan's Halobook prototype - Inquire - answering and suggesting questions\" src=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Vulcans-Halobook-prototype-Inquire-answering-and-suggesting-questions-1024x750.png\" alt=\"Vulcan's Halobook prototype - Inquire - answering and suggesting questions\" width=\"1024\" height=\"750\" srcset=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Vulcans-Halobook-prototype-Inquire-answering-and-suggesting-questions-1024x750.png 1024w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Vulcans-Halobook-prototype-Inquire-answering-and-suggesting-questions-300x219.png 300w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Vulcans-Halobook-prototype-Inquire-answering-and-suggesting-questions.png 1353w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/a><\/p>\n<p>In 2012, <a href=\"http:\/\/www.newscientist.com\/article\/mg21528765.700-the-intelligent-textbook-that-helps-students-learn.html\">72 freshman at De Anza College found that Inquire users, unlike students in control groups, obtained no grade lower than a C<\/a>.\u00a0 One of the perceived benefits was that students could ask questions that they might otherwise be embarrassed to ask a teacher.\u00a0 You can learn more about the application in the following video.<\/p>\n<p><object id=\"flashObj\" classid=\"clsid:d27cdb6e-ae6d-11cf-96b8-444553540000\" width=\"486\" height=\"412\" codebase=\"http:\/\/download.macromedia.com\/pub\/shockwave\/cabs\/flash\/swflash.cab#version=6,0,40,0\"><param name=\"bgcolor\" value=\"#FFFFFF\" \/><param name=\"flashVars\" value=\"videoId=2245896847001&amp;playerID=60836859001&amp;playerKey=AQ~~,AAAADiNHVuE~,igZFt8EUeHPwLKnVd0a_PFUvk7s-C-tC&amp;domain=embed&amp;dynamicStreaming=true\" \/><param name=\"base\" value=\"http:\/\/admin.brightcove.com\" \/><param name=\"seamlesstabbing\" value=\"false\" \/><param name=\"allowFullScreen\" value=\"true\" \/><param name=\"swLiveConnect\" value=\"true\" \/><param name=\"allowScriptAccess\" value=\"always\" \/><param name=\"src\" value=\"http:\/\/c.brightcove.com\/services\/viewer\/federated_f9?isVid=1\" \/><param name=\"name\" value=\"flashObj\" \/><param name=\"flashvars\" value=\"videoId=2245896847001&amp;playerID=60836859001&amp;playerKey=AQ~~,AAAADiNHVuE~,igZFt8EUeHPwLKnVd0a_PFUvk7s-C-tC&amp;domain=embed&amp;dynamicStreaming=true\" \/><param name=\"allowfullscreen\" value=\"true\" \/><embed id=\"flashObj\" type=\"application\/x-shockwave-flash\" width=\"486\" height=\"412\" src=\"http:\/\/c.brightcove.com\/services\/viewer\/federated_f9?isVid=1\" name=\"flashObj\" allowscriptaccess=\"always\" swliveconnect=\"true\" allowfullscreen=\"true\" seamlesstabbing=\"false\" base=\"http:\/\/admin.brightcove.com\" flashvars=\"videoId=2245896847001&amp;playerID=60836859001&amp;playerKey=AQ~~,AAAADiNHVuE~,igZFt8EUeHPwLKnVd0a_PFUvk7s-C-tC&amp;domain=embed&amp;dynamicStreaming=true\" bgcolor=\"#FFFFFF\"\/><\/object><\/p>\n<h2>The knowledge acquisition bottleneck<\/h2>\n<p>During 2010 and 2011, evidence began to accumulate indicating that the cost of knowledge acquisition using Aura was not falling enough for commericial viability.\u00a0 Although Aura could capture most of the knowledge in the text and encode background knowledge sufficient to answer roughly two thirds of reformulated AP exam questions, the cost for this level of performance remained above several thousand dollars per page.\u00a0 For a textbook like Campbell\u2019s biology, this would be in the millions of dollars.\u00a0 Although the resulting application could be profitable for such an expensive, high-volume textbook, the viability of acquiring the knowledge in hundreds of textbooks for deep question answer (QA) had not been established.\u00a0 Consequently, in 2012, Vulcan commissioned a KA experiment in which knowledge would be captured from English rather than using Aura\u2019s graphical approach.<\/p>\n<h2>Project Sherlock<\/h2>\n<p>In the KA experiment, Automata\u2019s patent-pending Linguist&#x2122; software was used to translate English sentences into formal logic and to translate the resulting logic into the maturing SILK system.\u00a0 Each of the sentences in a chapter of the textbook was interpreted using the Linguist.\u00a0 Then, each of the sentences was formalized into a logical axiom.\u00a0 Finally, the logical representation was translated into the syntax required by the SILK system.<\/p>\n<h2>The Linguist&#x2122;<\/h2>\n<p>The Linguist uses patent-pending methods to curate text into more formal logical semantics.\u00a0 Essentially, the Linguist accumulates knowledge from the web (or imported documents) into a wiki-like platform and annotates the content with precise lexical, syntactic, semantic, and logical information.\u00a0 The accumulated logical semantics are subsequently available for processing using semantic web and logical technologies.\u00a0 The core function of the Linguist, aside from annotation, is to engage users in disambiguating the meaning of sentences, as shown below.<\/p>\n<p><a href=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Collaborative-Knowledge-Acquisition-from-Web-Documents-byFaciliated-Natural-Language-Understanding-using-Automatas-Linguist.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-450\" title=\"Collaborative Knowledge Acquisition from Web Documents byFaciliated Natural Language Understanding using Automata's Linguist\" src=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Collaborative-Knowledge-Acquisition-from-Web-Documents-byFaciliated-Natural-Language-Understanding-using-Automatas-Linguist.png\" alt=\"Collaborative Knowledge Acquisition from Web Documents byFaciliated Natural Language Understanding using Automata's Linguist\" width=\"663\" height=\"617\" srcset=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Collaborative-Knowledge-Acquisition-from-Web-Documents-byFaciliated-Natural-Language-Understanding-using-Automatas-Linguist.png 663w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Collaborative-Knowledge-Acquisition-from-Web-Documents-byFaciliated-Natural-Language-Understanding-using-Automatas-Linguist-300x279.png 300w\" sizes=\"auto, (max-width: 663px) 100vw, 663px\" \/><\/a><\/p>\n<p>The client application used in the KA experiment is a <a href=\"http:\/\/en.wikipedia.org\/wiki\/Java_Web_Start\">Java-based web application<\/a> called KnowBuddy&#x2122; which uses a natural language processing (NLP) web service and a knowledge base service implemented in Java.\u00a0 The knowledge base server maintains a repository of the knowledge acquired with change management functionality, such as recording a history of user actions, including vocabulary, ontology, and sentence editing and histories.\u00a0 The clients and server cooperate in distributing information about ongoing activities across users as shown below.<\/p>\n<p><a href=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Real-time-knowledge-base-updating-of-collaborators-acquiring-knowledge-using-Automatas-Linguist.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-451\" title=\"Real-time knowledge base updating of collaborators acquiring knowledge using Automata's Linguist\" src=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Real-time-knowledge-base-updating-of-collaborators-acquiring-knowledge-using-Automatas-Linguist.png\" alt=\"Real-time knowledge base updating of collaborators acquiring knowledge using Automata's Linguist\" width=\"651\" height=\"362\" srcset=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Real-time-knowledge-base-updating-of-collaborators-acquiring-knowledge-using-Automatas-Linguist.png 651w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/2013\/05\/Real-time-knowledge-base-updating-of-collaborators-acquiring-knowledge-using-Automatas-Linguist-300x166.png 300w\" sizes=\"auto, (max-width: 651px) 100vw, 651px\" \/><\/a><\/p>\n<p>In the KA experiment, the Linguist used <a href=\"http:\/\/moin.delph-in.net\/PetTop\">PET, an open-source, natural language processing (NLP) system<\/a> implemented in C++ running as a web service under Linux and the <a href=\"http:\/\/www.delph-in.net\/erg\/\">English Resource Grammar (ERG)<\/a>, a large-vocabulary, high-precision, unification-based constituency grammar (other NLP systems, such as those which use statistical dependency grammars can also be supported).<\/p>\n<hr size=\"1\" \/>\n","protected":false},"excerpt":{"rendered":"<p>In the spring of 2012, Vulcan engaged Automata for a knowledge acquisition (KA) experiment.\u00a0 This article provides background on the context of that experiment and what the results portend for artificial intelligence applications, especially in the areas of education.\u00a0 Vulcan presented some of the award-winning work referenced here at an AI conference, including a demonstration &hellip; <\/p>\n<p class=\"link-more\"><a href=\"http:\/\/haleyai.com\/wordpress\/2013\/05\/28\/background-for-our-semantic-technology-2013-presentation\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Background for our Semantic Technology 2013 presentation&#8221;<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[72,10,12,13,15,16,21,22],"tags":[522,48,516,493,518,526,525,529,487,154,530,521,524,531,532,527,419,210,533,214,528,489,237,896,462,523,306],"class_list":["post-438","post","type-post","status-publish","format-standard","hentry","category-business-rules-management","category-formal-logic","category-knowledge-engineering","category-knowledge-management","category-methodology","category-natural-language","category-rules-engines","category-semantic-web","tag-aura","tag-automata","tag-deep-qa","tag-defeasible-logic","tag-digital-aristotle","tag-elearning","tag-electronic-publishing","tag-english-resource-grammar","tag-erg","tag-haley","tag-hpsg","tag-inquire","tag-intelligent-textbook","tag-knowbuddy","tag-knowledge-base","tag-linguist","tag-logic-programming","tag-natural-language-business-rules","tag-natural-logic","tag-nlp","tag-nlu","tag-pet","tag-project-halo","tag-question-answering","tag-silk","tag-sri-international","tag-vulcan"],"_links":{"self":[{"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/posts\/438","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/comments?post=438"}],"version-history":[{"count":18,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/posts\/438\/revisions"}],"predecessor-version":[{"id":1602,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/posts\/438\/revisions\/1602"}],"wp:attachment":[{"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/media?parent=438"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/categories?post=438"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/tags?post=438"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}