{"id":672951,"date":"2020-07-07T20:17:25","date_gmt":"2020-07-08T03:17:25","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=672951"},"modified":"2022-04-19T15:47:55","modified_gmt":"2022-04-19T22:47:55","slug":"predictive-program-synthesis","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/predictive-program-synthesis\/","title":{"rendered":"Predictive Program Synthesis"},"content":{"rendered":"<p>Program synthesis technologies help users to easily automate tasks that would otherwise require significant manual effort or programming skills. For instance, programming-by-example or natural language programming approaches allow the user to express intent by giving examples or natural language descriptions of the task, from which the system can synthesize a program in a formal programming language to complete the task. In this project, we are exploring the novel notion of <em>predictive program synthesis,<\/em> which is based on the idea that, in some scenarios, we can automatically suggest useful programs to the user without any interaction or intent specification from the user, based entirely on the context.<\/p>\n<p>Common examples of such scenarios include extraction of data from unstructured or semi-structured sources such as text files or webpages. We have developed technologies for automatically synthesizing data extraction scripts for such applications, and are also exploring other applications of predictive synthesis such as automatically suggesting improvements to code authored by developers in the IDE.<\/p>\n<p>Predictive synthesis is the technology being used for the <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/powerbi.microsoft.com\/ru-ru\/blog\/power-bi-desktop-april-2019-feature-summary\/#webByExample\">new web data extraction feature in Microsoft Power BI<span class=\"sr-only\"> (opens in new tab)<\/span><\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Program synthesis technologies help users to easily automate tasks that would otherwise require significant manual effort or programming skills. For instance, programming-by-example or natural language programming approaches allow the user to express intent by giving examples or natural language descriptions of the task, from which the system can synthesize a program in a formal programming [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13561,13556,13554,13560],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-672951","msr-project","type-msr-project","status-publish","hentry","msr-research-area-algorithms","msr-research-area-artificial-intelligence","msr-research-area-human-computer-interaction","msr-research-area-programming-languages-software-engineering","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"2017-07-07","related-publications":[334229,620757,702091,702169],"related-downloads":[],"related-videos":[676347,928641],"related-groups":[663303],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Sumit Gulwani","user_id":33755,"people_section":"Section name 0","alias":"sumitg"},{"type":"user_nicename","display_name":"Vu Le","user_id":39174,"people_section":"Section name 0","alias":"levu"},{"type":"user_nicename","display_name":"Arjun Radhakrishna","user_id":39405,"people_section":"Section name 0","alias":"arradha"},{"type":"user_nicename","display_name":"Daniel Perelman","user_id":39453,"people_section":"Section name 0","alias":"danpere"}],"msr_research_lab":[],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/672951","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":4,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/672951\/revisions"}],"predecessor-version":[{"id":673128,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/672951\/revisions\/673128"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=672951"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=672951"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=672951"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=672951"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=672951"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}