[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-639349-105":59,"doc-detail-639349-en":124},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":117,"head_meta":119,"extra_data":121,"updated_unix":123},105,"en","a-goal-driven-natural-language-interface-for-creating-application-integration-workflows","A Goal-Driven Natural Language Interface for Creating Application Integration Workflows","","Web applications and services are central to complex end-user goals, yet composing and integrating diverse cloud and application services remains labor-intensive when specified manually. GOFA (Goal Oriented Flow Assistant) generates application integration workflows from natural language using a three-stage pipeline: AMR parsing, knowledge-graph validation of candidate flows, and AI-planner composition. A deployed-system video demonstration supports the submission.",{"@graph":69,"@context":116},[70,84,99],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/a-goal-driven-natural-language-interface-for-creating-application-integration-workflows/639349/",{"url":83,"name":65,"@type":85,"author":86,"headline":65,"publisher":89,"fileFormat":92,"inLanguage":63,"description":67,"dateModified":93,"datePublished":93,"encodingFormat":92,"isAccessibleForFree":94,"interactionStatistic":95},"DigitalDocument",{"name":87,"@type":88},"ahduag","Person",{"url":74,"name":90,"@type":91},"DocShare","Organization","application/pdf","2026-10-22",true,{"@type":96,"interactionType":97,"userInteractionCount":4},"InteractionCounter",{"@type":98},"ViewAction",{"@type":100,"mainEntity":101},"FAQPage",[102,108,112],{"name":103,"@type":104,"acceptedAnswer":105},"What problem does GOFA address?","Question",{"text":106,"@type":107},"GOFA tackles the challenge of composing and integrating many cloud applications and services to achieve complex user goals, especially when users must specify workflows by hand.","Answer",{"name":109,"@type":104,"acceptedAnswer":110},"How does GOFA generate an integration workflow from a user sentence?",{"text":111,"@type":107},"It parses the utterance with Abstract Meaning Representation (AMR), validates candidate workflows using an Integration Knowledge Graph, and then composes the final workflow using an AI planner.",{"name":113,"@type":104,"acceptedAnswer":114},"What does the system use to validate candidate workflow options?",{"text":115,"@type":107},"GOFA uses a knowledge graph (Integration Knowledge Graph, IKG) to match structured representations against App Connect concepts and validate candidates.","https://schema.org",{"og:url":83,"og:type":118,"og:title":65,"og:site_name":90,"og:description":67},"article",{"robots":120,"canonical":83},"index,follow",{"doc_id":122,"site_id":62},639349,1792703231,{"code":4,"msg":5,"data":125},{"doc_id":122,"user_id":126,"nickname":87,"user_avatar":127,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":128,"file_id":129,"file_url":130,"file_type":131,"file_size":132,"view_count":4,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":81,"language":133,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":134,"faqs":135,"seo_title":136,"seo_description":67,"update_tm":123,"read_time":39},3985747870414,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","A Goal-Driven Natural Language Interface for Creating Application Integration Work􀀃ows  \nMichelle Brachman 1 , Christopher Bygrave2 , Tathagata Chakraborti 1 , Arunima Chaudhary 1 , Zhining Ding3 , Casey Dugan 1 , David Gros4 , Thomas Gschwind 1 , James Johnson 1 , Jim Laredo 1 , Christoph Miksovic 1 , Qian Pan 1 , Priyanshu Rai5 , Ramkumar Ramalingam2 , Paolo Scotton 1 , Nagarjuna Surabathina2 ,  \nKartik Talamadupula 1  \n1IBM Research 2IBM Cloud & Cognitive Software 3Wellesley College 4UC Davis 5Persistent Systems  \nAbstract  \nWeb applications and services are increasingly important in a distributed internet 􀀂lled with diverse cloud services and applications, each of which enable the completion of narrowly de􀀂ned tasks. Given the explosion in the scale and diversity of such services, their composition and integration for achieving complex user goals remains a challenging task for endusers and requires a lot of development effort when speci􀀂ed by hand. We present a demonstration of the Goal Oriented Flow Assistant (GOFA) system, which provides a natural language solution to generate work􀀃ows for application integration. Our tool is built on a three-step pipeline: it 􀀂rst uses Abstract Meaning Representation (AMR) to parse utterances; it then uses a knowledge graph to validate candidates; and 􀀂 -nally uses an AI planner to compose the candidate 􀀃ow. We provide a video demonstration of the deployed system as part of our submission.  \nIntroduction  \nIn the cloud and application driven internet of today, the composition and integration of various application constituted work􀀃ows is an important problem. Many end-user tasks cannot be accomplished without composing (connecting) different applications together in an integration 􀀃ow. This task 􀂖 akin to web service composition (Srivastava and Koehler 2003; Hoffmann, Bertoli, and Pistore 2007) 􀂖 is a common development task for programmers and nonprogrammers, and can bene􀀂t from automation (Gschwind 2002) . Recently, enterprise industrial tools like App Connect 1 , Zapier 2 , and Microsoft Power Automate 3 have begun to provide visual and form-based end-user programming environments for application integration. Even in such end-user programming environments, users still face significant barriers (Ko, Myers, and Aung 2004): (i) the signi􀀂 -cant scale and diversity of the number of applications renders discovery a tedious and oftentimes impossible task; and (ii) the variety and complexity of the inputs and outputs of various applications introduces additional barriers to handcrafted composition by users.  \nCopyright © 2022, Association for the Advancement of Arti􀀂cial Intelligence ([www.aaai.org](www.aaai.org)). All rights reserved.  \n1[https://www.ibm.com/cloud/app-connect](https://www.ibm.com/cloud/app-connect)  \n2[https://zapier.com](https://zapier.com)  \n3[https://powerautomate.microsoft.com](https://powerautomate.microsoft.com)  \nNatural language has the potential to reduce barriers and learning curves for complex tasks (Linder et al. 2013; Sales, Handschuh, and Freitas 2017), like end-user programming for web service and application composition. Even for users with suf􀀂cient programming experience, natural language generation of service composition tasks could increase the ef􀀂ciency of the interaction and composition by reducing GUI interactions and by providing automatically generated 􀀃ow candidates. In this paper, we introduce the GoalOriented Flow Assist (GOFA) system 􀂖 a system that generates web application integration 􀀃ows from natural language in the context of App Connect. GOFA automatically produces application integration 􀀃ows from a user utterance speci􀀂ed as a natural language sentence. GOFA uses a three step pipeline: 1) utterance parsing with AMR, 2) validation of candidates with Knowledge Graph, and 3) composition with an AI planner.  \nBackground  \nOur system has been implemented within App Connect. App Connect is a GUI-based tool that enables users to create applica","cbCaijAcBqmAfM6W","https://ap.wps.com/l/cbCaijAcBqmAfM6W","pdf",98935,"English","# Abstract\n# Introduction\n# Background\n# Goal Oriented Flow Assist (GOFA)\n## Abstract Meaning Representation (AMR)","[{\"question\":\"What problem does GOFA address?\",\"answer\":\"GOFA tackles the challenge of composing and integrating many cloud applications and services to achieve complex user goals, especially when users must specify workflows by hand.\"},{\"question\":\"How does GOFA generate an integration workflow from a user sentence?\",\"answer\":\"It parses the utterance with Abstract Meaning Representation (AMR), validates candidate workflows using an Integration Knowledge Graph, and then composes the final workflow using an AI planner.\"},{\"question\":\"What does the system use to validate candidate workflow options?\",\"answer\":\"GOFA uses a knowledge graph (Integration Knowledge Graph, IKG) to match structured representations against App Connect concepts and validate candidates.\"}]","A Goal-Driven Natural Language Interface for Creating Application Integration Workflows | PDF"]