While editing code, it is common for developers to make multiple related repeated edits that are all instances of a more general program transformation. Since this process can be tedious and error-prone, we study the problem of automatically learning program transformations from past edits, which can then be used to predict future edits. We take a novel view of the problem as a semi-supervised learning problem: apart from the concrete edits that are instances of the general transformation, the learning procedure also exploits access to additional inputs (program subtrees) that are marked as positive or negative depending on whether the transformation applies on those inputs. We present a procedure to solve the semi-supervised transformation learning problem using anti-unification and programming-by-example synthesis technology. To eliminate reliance on access to marked additional inputs, we generalize the semi-supervised learning procedure to a feedback-driven procedure that also generates the marked additional inputs in an iterative loop. We apply these ideas to build and evaluate three applications that use different mechanisms for generating feedback. Compared to existing tools that learn program transformations from edits, our feedback-driven semi-supervised approach is vastly more effective in successfully predicting edits with significantly lesser amounts of past edit data.<\/p>\n","protected":false},"excerpt":{"rendered":"
While editing code, it is common for developers to make multiple related repeated edits that are all instances of a more general program transformation. Since this process can be tedious and error-prone, we study the problem of automatically learning program transformations from past edits, which can then be used to predict future edits. We take […]<\/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":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556,13560],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-683394","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-programming-languages-software-engineering","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2020-10-1","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"ACM","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/08\/OOPSLA_2020___Semi_Supervised_Program_Synthesis_for_Edit_Suggestion.pdf","id":"702190","title":"oopsla_2020___semi_supervised_program_synthesis_for_edit_suggestion","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":702190,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/10\/OOPSLA_2020___Semi_Supervised_Program_Synthesis_for_Edit_Suggestion.pdf"},{"id":683514,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/08\/OOPSLA_2020___Semi_Supervised_Program_Synthesis_for_Edit_Suggestion-2.pdf"},{"id":683448,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/08\/OOPSLA_2020___Semi_Supervised_Program_Synthesis_for_Edit_Suggestion-1.pdf"}],"msr-author-ordering":[{"type":"text","value":"Xiang Gao","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Shraddha Barke","user_id":43605,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Shraddha Barke"},{"type":"user_nicename","value":"Arjun Radhakrishna","user_id":39405,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Arjun Radhakrishna"},{"type":"user_nicename","value":"Gustavo Soares","user_id":39183,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Gustavo Soares"},{"type":"user_nicename","value":"Sumit Gulwani","user_id":33755,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Sumit Gulwani"},{"type":"text","value":"Alan Leung","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Nachi Nagappan","user_id":33044,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Nachi Nagappan"},{"type":"user_nicename","value":"Ashish Tiwari","user_id":39171,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ashish Tiwari"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[851368],"msr_group":[144672,663303],"msr_project":[670944],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":670944,"post_title":"Blue-Pencil: modeless program synthesis","post_name":"modeless-program-synthesis","post_type":"msr-project","post_date":"2020-07-01 16:46:01","post_modified":"2022-04-19 15:08:42","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/modeless-program-synthesis\/","post_excerpt":"Blue-Pencil aim at developing modeless program synthesis systems, that is, systems that do not require users do not explicitly enter a special mode to give demonstration or examples. Instead, a modeless program synthesis system observes what task a user is doing, learn how to automate the task from those observations, and subsequently assist the user by automating the remaining part of the task.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/670944"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/683394"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":6,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/683394\/revisions"}],"predecessor-version":[{"id":1093176,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/683394\/revisions\/1093176"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=683394"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=683394"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=683394"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=683394"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=683394"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=683394"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=683394"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=683394"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=683394"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=683394"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=683394"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=683394"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=683394"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=683394"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=683394"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=683394"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}