[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118954-en":3,"doc-seo-118954-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118954,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",6,"Technology","AI2 The next leap toward native language-based and explainable machine learning framework","Machine learning frameworks expanded across decades, moving AI from academia into enterprise settings, yet still fall short of new usability expectations. The AI2 framework introduces a natural-language interface enabling non-specialists to run machine learning algorithms through English commands without programming knowledge. It adds greenhouse-gas awareness by estimating algorithm-generated emissions and suggesting alternatives to avoid energy-intensive runs. A preprocessing module guides proper dataset description, normalization, loading, and splitting, while explainability replaces the traditional black-box limitation with textual, graphical, and tabular explanations of the algorithm’s process and results.","Springer Nature 2021 LATEX template  \nPOSTPRINT VERSION. The final version is published here :  \nDessureault, J.-S. et Massicotte, D. (2023) . AI2: the next leap toward native language-based and explainable machine learning framework. Automated Software  \nEngineering (Vol. 30, p. 32) . doi: [https://doi.org/10.1007/s10515-023-00399-5](https://doi.org/10.1007/s10515-023-00399-5)  \nAI 2 : The next leap toward native language  \nbased and explainable machine learning framework  \nJean-Sébastien Dessureault 1* and Daniel Massicotte 1  \n1* LSSI, Electrical engineering, Université du Québec à  \nTrois-Rivières, 3351 Bd des Forges, Trois-Rivières, G8Z 4M3, Québec, Canada.  \n*Corresponding author(s) . E-mail(s):  \n[jean.sebastien.dessureault@cegeptr.qc.ca](jean.sebastien.dessureault@cegeptr.qc.ca) ;  \nContributing authors: [daniel.massicotte@uqtr.ca](daniel.massicotte@uqtr.ca) ;  \nAbstract  \nThe machine learning frameworks flourished in the last decades, allow  \ning artificial intelligence to get out of academic circles to be applied  \nto enterprise domains. This field has significantly advanced, but there  \nis still some meaningful improvement to reach the subsequent expec  \ntations. The proposed framework, named AI2 , uses a natural language  \ninterface that allows a non-specialist to benefit from machine learning  \nalgorithms without necessarily knowing how to program with a pro  \ngramming language. The primary contribution of the AI2 framework  \nallows a user to call the machine learning algorithms in English, mak  \ning its interface usage easier. The second contribution is greenhouse gas  \n(GHG) awareness. It has some strategies to evaluate the GHG gener  \nated by the algorithm to be called and to propose alternatives to find  \na solution without executing the energy-intensive algorithm. Another  \ncontribution is a preprocessing module that helps to describe and to  \nload data properly. Using an English text-based chatbot, this module  \nguides the user to define every dataset so that it can be described, nor  \nmalized, loaded and divided appropriately. The last contribution of this  \npaper is about explainability. For decades, the scientific community has  \nknown that machine learning algorithms imply the famous black-box  \nproblem. Traditional machine learning methods convert an input into  \nan output without being able to justify this result. The proposed frame  \nwork explains the algorithm’s process with the proper texts, graphics  \nSpringer Nature 2021 LATEX template  \n2 AI2 The next leap toward native language based and explainable machine learning fr  \nand tables. The results, declined in five cases, present usage applications  \nfrom the user’s English command to the explained output. Ultimately,  \nthe AI2 framework represents the next leap toward native language  \nbased, human-oriented concerns about machine learning framework.  \nKeywords: machine learning; framework; NLP; AI ethics; explainability  \n1 Introduction  \nTwo decades ago, some popular algorithms existed and were well documented in scientific literacy, but there was still no easy way to use them. Scientists had to read the equations and the algorithm before implementing it in the desired programming language. Every matrix had to be multiplied, and every derivative had to be computed by the scientist’s code. In the last two decades, machine learning has finally flourished. One of the most meaningful frameworks was certainly TensorFlow [1] . This powerful tool helped the community accelerate development and democratize the machine learning field. It helped this field of knowledge reach a more comprehensive range of applicative projects instead of being restricted to academics.  \nA few years after the first version of Tensorflow, many others came to the machine learning community. Among the most popular: Scikit-Learn, CNTK, Torch, Matlab, and Keras [2] . In the last few years, a user-friendly framework with a graphical interface named Orange [3] became available, aimi","cbCaicdxMC5qbXLu","https://ap.wps.com/l/cbCaicdxMC5qbXLu","pdf",541550,1,29,"English","en",105,"# Introduction\n## Machine learning frameworks and usability challenges\n## Related work and performance comparisons\n## Explainable and interpretable approaches\n# AI2 framework overview\n## Natural-language interface with English chatbot\n## Greenhouse gas awareness strategies\n## Preprocessing and dataset guidance\n## Explainability and black-box mitigation","[{\"question\":\"What is the main purpose of the AI2 framework?\",\"answer\":\"AI2 provides a natural-language interface so non-specialists can use machine learning algorithms via English commands without needing to program.\"},{\"question\":\"How does AI2 address greenhouse-gas (GHG) concerns?\",\"answer\":\"AI2 includes strategies to evaluate GHG generated by the algorithm and proposes alternatives to find solutions without executing energy-intensive runs.\"},{\"question\":\"What does explainability mean in AI2?\",\"answer\":\"AI2 explains the algorithm’s internal process using appropriate texts, graphics, and tables, helping address the classic black-box problem.\"}]","AI2 The next leap toward native language-based and explainable machine learning framework | PDF",1785721183,73,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"ai2-the-next-leap-toward-native-language-based-and-explainable-machine-learning-framework","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/ai2-the-next-leap-toward-native-language-based-and-explainable-machine-learning-framework/118954/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main purpose of the AI2 framework?","Question",{"text":75,"@type":76},"AI2 provides a natural-language interface so non-specialists can use machine learning algorithms via English commands without needing to program.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does AI2 address greenhouse-gas (GHG) concerns?",{"text":80,"@type":76},"AI2 includes strategies to evaluate GHG generated by the algorithm and proposes alternatives to find solutions without executing energy-intensive runs.",{"name":82,"@type":73,"acceptedAnswer":83},"What does explainability mean in AI2?",{"text":84,"@type":76},"AI2 explains the algorithm’s internal process using appropriate texts, graphics, and tables, helping address the classic black-box problem.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,113,118,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]