{"id":690276,"date":"2020-09-21T12:33:26","date_gmt":"2020-09-21T19:33:26","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?p=690276"},"modified":"2020-10-06T16:26:57","modified_gmt":"2020-10-06T23:26:57","slug":"dialogue-as-dataflow-a-new-approach-to-conversational-ai","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/en-us\/research\/blog\/dialogue-as-dataflow-a-new-approach-to-conversational-ai\/","title":{"rendered":"Dialogue as Dataflow: A new approach to conversational AI"},"content":{"rendered":"\n
By the Semantic Machines research team<\/em><\/p>\n\n\n\n \u201cEasier said than done.\u201d These four words reflect the promise of conversational AI. It takes just seconds to ask When are Megan and I both free?<\/em> but much longer to find out manually from a calendar. Indeed, almost everything we do with technology can feel like a long path to a short goal. At Microsoft Semantic Machines<\/a>, we’re working to bridge this gap\u2014to build conversational AI experiences where you can focus on saying what you want and the system will worry about how to get it done. You should be able to speak as you speak to a friend: naturally, contextually, and collaboratively.<\/p>\n\n\n\n A truly powerful conversational AI needs to do more than deeply understand language<\/em>. To be contextual, flexible, and robust, the AI must also deeply understand actions<\/em>\u2014most goals involve multiple steps and multiple sources of information. Representing goals, actions, and dialogue states is one of the central challenges in conversational AI systems. Our new paper in Transactions of the Association for Computational Linguistics (TACL)<\/em>, titled \u201cTask-Oriented Dialogue as Dataflow Synthesis, (opens in new tab)<\/span><\/a>\u201d describes a new representation and modeling framework that interprets dialogues as dataflow graphs, enabling conversations about complex tasks that span multiple domains. We\u2019re also releasing a dataset of over 40,000 dialogues annotated with dataflow graphs and a public leaderboard (opens in new tab)<\/span><\/a>, to help the AI community work on challenging and realistic problems in multi-turn, task-oriented dialogue.<\/p>\n\n\n\n Our new dataset illustrates the incredible diversity of user requests:<\/p>\n\n\n\n Traditional “slotfilling” dialogue systems ignore much of this diversity. They support only a stock set of goals, and they have no representation of context beyond a list of arguments missing from the current goal. At the other extreme, recent “end-to-end” neural dialogue systems are free in principle to learn arbitrary context-dependent responses, but it\u2019s not enough to be flexible in the words used because dialogue also requires flexibility in the actions performed. Deployed systems also have requirements of controllability and truthfulness that are challenging in unstructured systems.<\/p>\n\n\n\n\t \n\t\tSpotlight: Event<\/span>\n\t<\/p>\n\t\n\t Microsoft is a proud sponsor and active participant of\u00a0CVPR 2024<\/a>, which focuses on advancements in computer vision and pattern recognition. <\/p>\n\t\t\t\t\n\t\t\t\t\t\t\t\t\n\t\t
Microsoft at CVPR 2024<\/h2>\n\t\t\t\t\n\t\t\t\t\t\t\t\t