Summary:<\/em><\/strong> \u00a0Contextually intelligent, NLP-based interactive assistants are one of the next big things for AI\/ML.\u00a0 The tech is already here from recommendation engines.\u00a0 The need to be more efficient and to become AI-augmented in our decision making is now.\u00a0 Getting the contextual awareness is the hard part.<\/em><\/p>\n \u00a0<\/p>\n In retrospect I wish there were a more concise agreed naming convention for this bit of technical legerdemain.\u00a0 \u201cInclusive\u201d and \u201ccontextually sensitive\u201d are in the category of those \u2018suitcase words\u2019 Marvin Minsky called out as being so dependent on the user\u2019s experience that agreement on meaning is difficult.<\/p>\n What we\u2019re not talking about is the ability of NLP to hold a contextually appropriate conversation, such as making a reasonable response or request for clarification based on the topic at hand.\u00a0 For the most part, short of performing psychoanalysis, chatbots can do pretty well with human ad hoc conversation.<\/p>\n Also, we\u2019re not talking about being culturally inclusive as in detecting and eliminating bias.\u00a0 Important, but not what we\u2019re getting at.<\/p>\n What we\u2019re describing is the next big step in NLP utility<\/u> in which the NLP puts together facts it knows about us and proactively takes action or makes suggestions that make our life easier.<\/p>\n The example we gave in our previous article is about having the NLP assistant remind me of my mother\u2019s upcoming birthday in a week or so without my having explicitly created a reminder.\u00a0 More importantly my NLP assistant could make a recommendation for a present.\u00a0 Presumably my past communications with her both in fact and tone contain some strong signals about my mom\u2019s demographics and perhaps even her interests so why not predict a short list of appropriate gifts.\u00a0 Now that would be valuable.<\/p>\n So perhaps a better description of this behavior then would be \u2018contextually intelligent\u2019.\u00a0 We\u2019ll stick with that.<\/p>\n \u00a0<\/p>\n Helping Make Decisions<\/strong><\/span><\/p>\n The base technology for this advancement is the already well developed field of recommendation engines.\u00a0 Thus far these have been the bread and butter of ecommerce whether recommending books, airplane flights, or love interests.\u00a0 What is coming is the expansion of this tech from predicting things you might like, to actions you might take and then helping you make that decision.<\/p>\n One element of this problem is that we have to add information to make these more sophisticated recommendations.\u00a0 The close-in sources are our calendars, email, and texts with other sources added as the field develops.\u00a0 As it happens, calendar and email-aware intelligent assistants are in early research and development, making this a lead candidate for our next break through.<\/p>\n But beyond adding information sources, the challenge is how to integrate this into a useful tool and that requires a deeper understanding of how people make decisions.\u00a0 For example, your intelligent assistant may be able to predict what your next action could be, but how comfortable will you be if the IA simply says \u2018now do this\u2019.<\/p>\n Our decision making is typically built on a filter of what\u2019s possible.\u00a0 That is we look at the options (like different airline flights) and understanding those options we make a decision.\u00a0 That filtering of possibilities is a major challenge.\u00a0 Present too much information about the how the recommended action was made and we bury the user in the paradox of too many options.\u00a0 Present little or no underlying decision data and the user\u2019s comfort and willingness to accept the action plummets.<\/p>\n \u00a0<\/p>\n Defining Context<\/strong><\/span><\/p>\n This ability to help make decisions is clearly going to start small before it expands, and in terms of email and calendars the contextual information that can be extracted is most likely to be about what will happen, when will it happen, and which people will be involved.<\/p>\n A first step, knowing these three things, might be to figure out what you\u2019re going to need in advance of that event to help you prepare and participate.\u00a0 This begins to look like the behavior a really great personal assistant might display in helping you get ready without your really having to tell them explicitly what you need.<\/p>\n We all attend a lot of meetings and it\u2019s no stretch to say that the content and goal of each calendar event is not on our top of mind.\u00a0 Wouldn\u2019t it be great if your IA could assemble the documents and information you need, anticipate how to manage your time to get ready, or even provide you with a list of information you might need on-the-instant during the meeting.\u00a0 It might also provide you with a synopsis of previous meetings leading up to this one.<\/p>\n A more advance scenario might be where you are managing several parallel projects.\u00a0 Since you are the common thread, it\u2019s likely that these project schedules are interlinked at some point in the future that defines the critical path and might block one project from proceeding until other elements in a separate project are complete.\u00a0 A contextually intelligent IA could be trained to foresee those scheduling conflicts even months ahead of time and alert you.<\/p>\n \u00a0<\/p>\n Efficiency First \u2013 Augmented Decision Making Follows<\/strong><\/span><\/p>\n At the outset of contextually intelligent assistants, the most likely goal is to simply be more efficient with our time, to be able to focus on what\u2019s important and let the IA coordinate the details.<\/p>\n But the magic may be in the way the IA can present information.\u00a0 Once the IA has achieved a contextual understanding of your goals and actions, the next thing you\u2019ll need is information.\u00a0 Eventually IAs should be able to reach beyond the information you already have captured in your various devices and through communication to recommend other sources.<\/p>\n Think of a young programmer who brings a certain set of skills and knowledge with them.\u00a0 Chances are this includes web sites or specific libraries or notebooks the person is used to relying on.\u00a0 The future intelligent IA might propose solutions from different sources, accelerating the learning curve and success of that beginner.<\/p>\n \u00a0<\/p>\n Remembering What You Forgot<\/strong><\/span><\/p>\n Beyond simple calendar reminders you might create, your advanced IA might detect when we\u2019ve forgotten something.\u00a0 For example, your wife emails that you should make restaurant reservations and arrange for a babysitter for your night out next Friday.\u00a0 You make the restaurant reservations but get distracted by the next task at hand and forget about the babysitter.\u00a0 Your IA might reasonably detect the omission of this action and remind you.\u00a0 Disaster averted.<\/p>\n \u00a0<\/p>\n What About Privacy<\/strong><\/span><\/p>\n This will be an important concern for next gen IAs.\u00a0 Data gathering is likely to go well beyond your calendar and email to include even your eye movements, your cursor movements, and particularly outside data sources.\u00a0<\/p>\n For example in tuning models to discover words that are important to you, the model needs to train on your data but needs to be constrained so that it doesn\u2019t give something away when generating communication.\u00a0 If it saw that discussing your new job at a competitor was suddenly a common theme in your email, that\u2019s not something you\u2019d want your IA showing to anyone.\u00a0 As with so many things AI, privacy will be an ongoing challenge.<\/p>\n The case is strong that contextually intelligent NLP interactive assistants can be the \u2018next big thing\u2019 in AI\/ML.\u00a0 The tech is here.\u00a0 The development is underway.\u00a0 Soon we may all be able to have our own super prescient Radar O\u2019Reilly, or Tony Stark\u2019s digital assistant Jarvis at our own beck and call.<\/p>\n \u00a0<\/p>\n \u00a0<\/p>\n Other articles by Bill Vorhies<\/u><\/em><\/a><\/p>\n \u00a0<\/p>\n About the author:\u00a0 Bill is Contributing Editor for Data Science Central.\u00a0 Bill is also President & Chief Data Scientist at Data-Magnum and has practiced as a data scientist since 2001.\u00a0 His articles have been read more than 2 million times.<\/p>\n He can be reached at:<\/p>\n Bill@DataScienceCentral.com<\/a> or<\/span> Bill@Data-Magnum.com<\/a><\/p>\n<\/div>\n Go to Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" Author: William Vorhies Summary: \u00a0Contextually intelligent, NLP-based interactive assistants are one of the next big things for AI\/ML.\u00a0 The tech is already here from recommendation […] Read More<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":468,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_bbp_topic_count":0,"_bbp_reply_count":0,"_bbp_total_topic_count":0,"_bbp_total_reply_count":0,"_bbp_voice_count":0,"_bbp_anonymous_reply_count":0,"_bbp_topic_count_hidden":0,"_bbp_reply_count_hidden":0,"_bbp_forum_subforum_count":0,"footnotes":""},"categories":[26],"tags":[],"_links":{"self":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts\/2749"}],"collection":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/comments?post=2749"}],"version-history":[{"count":0,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts\/2749\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/media\/460"}],"wp:attachment":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/media?parent=2749"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/categories?post=2749"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/tags?post=2749"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}<\/a>Last week we took the position that from a technical standpoint, \u2018deeply inclusive and contextually sensitive\u2019 AI is one of the two \u2018next big things\u2019 in AI<\/u><\/em><\/a>.<\/p>\n