The rapidly increasing ubiquity of computing puts a great demand on next-generation human-machine interfaces. Natural language interfaces, exemplified by virtual assistants like Apple Siri and Microsoft Cortana, are widely believed to be a promising direction. However, current natural language interfaces provide users with little help in case of incorrect interpretation of user commands. We hypothesize that the support of fine-grained user interaction can greatly improve the usability of natural language interfaces. In the specific setting of natural language interfaces to web APIs, we conduct a systematic study to verify our hypothesis. To facilitate this study, we propose a novel modular sequence-to-sequence model to create interactive natural language interfaces. By decomposing the complex prediction process of a typical sequence-to-sequence model into small, highly-specialized prediction units called modules, it becomes straightforward to explain the model prediction to the user, and solicit user feedback to correct possible prediction errors at a fine-grained level. We test our hypothesis by comparing an interactive natural language interface with its non-interactive version through both simulation and human subject experiments with real-world APIs. We show that with interactive natural language interfaces, users can achieve a higher success rate and a lower task completion time, which lead to greatly improved user satisfaction.<\/p>\n","protected":false},"excerpt":{"rendered":"
The rapidly increasing ubiquity of computing puts a great demand on next-generation human-machine interfaces. Natural language interfaces, exemplified by virtual assistants like Apple Siri and Microsoft Cortana, are widely believed to be a promising direction. However, current natural language interfaces provide users with little help in case of incorrect interpretation of user commands. We hypothesize […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556,13545,13555],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-479364","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-human-language-technologies","msr-research-area-search-information-retrieval","msr-locale-en_us"],"msr_publishername":"ACM","msr_edition":"Proceedings of the 41th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2018)","msr_affiliation":"","msr_published_date":"2018-07-08","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":"492839","msr_publicationurl":"http:\/\/sigir.org\/sigir2018\/","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"sigir18_nl2api","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2018\/04\/sigir18_nl2api.pdf","id":492839,"label_id":0},{"type":"url","title":"http:\/\/sigir.org\/sigir2018\/","viewUrl":false,"id":false,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":0,"url":"http:\/\/sigir.org\/sigir2018\/"},{"id":492839,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2018\/06\/sigir18_nl2api.pdf"}],"msr-author-ordering":[{"type":"text","value":"Yu Su","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Ahmed Hassan Awadallah","user_id":31979,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ahmed Hassan Awadallah"},{"type":"text","value":"Miaosen Wang","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Ryen W. White","user_id":33481,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ryen W. White"}],"msr_impact_theme":[],"msr_research_lab":[199565],"msr_event":[],"msr_group":[392600,493619],"msr_project":[724078],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/479364"}],"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":4,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/479364\/revisions"}],"predecessor-version":[{"id":561855,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/479364\/revisions\/561855"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=479364"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=479364"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=479364"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=479364"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=479364"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=479364"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=479364"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=479364"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=479364"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=479364"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=479364"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=479364"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=479364"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=479364"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=479364"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}