Code completion is usually cast as a language modelling problem, ie, continuing an input in a left-to-right fashion. However, in practice, some parts of the completion (eg, string literals) may be very hard to predict, whereas subsequent parts directly follow from the context. To handle this, we instead consider the scenario of generating code completions with” holes” inserted in places where a model is uncertain.<\/p>\n
We develop Grammformer, a Transformer-based model that guides the code generation by the programming language grammar, and compare it to a variety of more standard sequence models. We train the models on code completion for C# and Python given partial code context. To evaluate models, we consider both ROUGE as well as a new metric RegexAcc that measures success of generating completions matching long outputs with as few holes as possible. In our experiments, Grammformer generates 10-50% more accurate completions compared to traditional generative models and 37-50% longer sketches compared to sketch-generating baselines trained with similar techniques.<\/p>\n","protected":false},"excerpt":{"rendered":"
Code completion is usually cast as a language modelling problem, ie, continuing an input in a left-to-right fashion. However, in practice, some parts of the completion (eg, string literals) may be very hard to predict, whereas subsequent parts directly follow from the context. To handle this, we instead consider the scenario of generating code completions […]<\/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":[259120],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-823873","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":"2022-4-1","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":"","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":"url","viewUrl":"false","id":"false","title":"https:\/\/openreview.net\/pdf?id=q79uMSC6ZBT","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"guest","value":"daya-guo","user_id":772999,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=daya-guo"},{"type":"user_nicename","value":"Alexey Svyatkovskiy","user_id":40672,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Alexey Svyatkovskiy"},{"type":"guest","value":"jian-yin","user_id":769480,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=jian-yin"},{"type":"user_nicename","value":"Nan Duan","user_id":33052,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Nan Duan"},{"type":"user_nicename","value":"Marc Brockschmidt","user_id":32763,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Marc Brockschmidt"},{"type":"user_nicename","value":"Miltos Allamanis","user_id":37267,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Miltos Allamanis"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[831184],"msr_group":[776485],"msr_project":[875721,323543],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":875721,"post_title":"Code Intelligence","post_name":"code-intelligence","post_type":"msr-project","post_date":"2022-09-07 02:13:28","post_modified":"2022-09-07 02:13:32","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/code-intelligence\/","post_excerpt":"Apply AI techniques for software engineering Code intelligence project aims to leverage AI techniques to help software developers improve the productivity of the development process. We focus on building large-scale pre-trained models to understand and generate source codes. The research directions include pre-trained models for code, benchmark datasets, code completion, code retrieval, code review, etc. More AI-assisted products under collaboration with DevDiv, GitHub, and LinkedIn will be released which can empower the software developers all…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/875721"}]}},{"ID":323543,"post_title":"Deep Program Understanding","post_name":"deep-program-understanding","post_type":"msr-project","post_date":"2017-05-02 03:55:00","post_modified":"2022-03-03 01:28:05","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/deep-program-understanding\/","post_excerpt":"The Deep Program Understanding project aims to teach machines to understand complex algorithms, combining methods from the programming languages, software engineering and the machine learning communities.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/323543"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/823873"}],"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":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/823873\/revisions"}],"predecessor-version":[{"id":823879,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/823873\/revisions\/823879"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=823873"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=823873"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=823873"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=823873"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=823873"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=823873"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=823873"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=823873"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=823873"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=823873"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=823873"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=823873"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=823873"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=823873"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=823873"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=823873"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}