[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-563994-105":53,"doc-detail-563994-en":126},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":119,"head_meta":121,"extra_data":123,"updated_unix":125},105,"en","text2chart-a-multi-staged-chart-generator-from-natural-language-text","Text2Chart - A Multi-Staged Chart Generator from Natural Language Text","","Generation of scientific visualization from analytical natural language text is a challenging task. This paper proposes Text2Chart, a multi-staged chart generator that converts natural language input into two-dimensional charts. The method extracts x- and y-axis entities, maps x-entities to corresponding y-entities, and predicts a suitable chart type (bar, line, or pie). A dedicated dataset and supervised models are built and evaluated with multiple metrics, showing strong overall effectiveness for chart formation.",{"@graph":63,"@context":118},[64,80,101],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":11,"@type":70,"position":76},"https://docshare.wps.com/template/presentations/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/text2chart-a-multi-staged-chart-generator-from-natural-language-text/563994/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/text2chart-a-multi-staged-chart-generator-from-natural-language-text/563994.png","ImageObject",442,249,{"name":88,"@type":89},"Cipher","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-10-20","2026-10-12",true,{"@type":98,"interactionType":99,"userInteractionCount":47},"InteractionCounter",{"@type":100},"ViewAction",{"@type":102,"mainEntity":103},"FAQPage",[104,110,114],{"name":105,"@type":106,"acceptedAnswer":107},"What is Text2Chart and what does it generate?","Question",{"text":108,"@type":109},"Text2Chart is a multi-staged chart generator that takes analytical natural language text as input and produces two-dimensional scientific charts.","Answer",{"name":111,"@type":106,"acceptedAnswer":112},"How does Text2Chart handle the chart generation process?",{"text":113,"@type":109},"It operates in three stages: identifying x- and y-axis entities, mapping x-entities to y-entities, and predicting the best chart type among bar, line, and pie.",{"name":115,"@type":106,"acceptedAnswer":116},"Which models and methods are reported as best-performing for each stage?",{"text":117,"@type":109},"The first stage uses BERT embeddings with LSTM for x/y entity labeling, the mapping stage uses Random Forest, and the chart-type prediction stage uses fastText embeddings with LSTM layers.","https://schema.org",{"og:url":78,"og:type":120,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":122,"canonical":78},"index,follow",{"doc_id":124,"site_id":56},563994,1792241704,{"code":4,"msg":5,"data":127},{"doc_id":124,"user_id":128,"nickname":88,"user_avatar":129,"doc_module":9,"category_id":8,"category_name":11,"doc_title":59,"doc_description":61,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":47,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":45,"language":135,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":136,"faqs":137,"seo_title":138,"seo_description":61,"update_tm":139,"read_time":140},687208528416,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","arXiv :2104 .04584v 1 [ cs .CL] 9 Apr 2021  \nText2Chart: A Multi-Staged Chart Generator from Natural  \nLanguage Text  \nMd. Mahinur Rashid, Hasin Kawsar Jahan, Annysha Huzzat, Riyasaat Ahmed Rahul, Tamim Bin Zakir, Farhana Meem, Md. Saddam Hossain Mukta and Swakkhar Shatabda ∗  \nDepartment of Computer Science and Enginnering, United International University  \nAbstract  \nGeneration of scienti􀀌c visualization from analytical natural language text is a challenging task. In this paper, we propose Text2Chart, a multi-staged chart generator method. Text2Chart takes natural language text as input and produce visualization as two-dimensional charts. Text2Chart approaches the problem in three stages. Firstly, it identi􀀌es the axis elements of a chart from the given text known as x and y entities. Then it 􀀌nds a mapping of x-entities with its corresponding y-entities. Next, it generates a chart type suitable for the given text: bar, line or pie. Combination of these three stages is capable of generating visualization from the given analytical text. We have also constructed a dataset for this problem. Experiments show that Text2Chart achieves best performances with BERT based encodings with LSTM models in the 􀀌rst stage to label x and y entities, Random Forest classi􀀌er for the mapping stage and fastText embedding with LSTM for the chart type prediction. In our experiments, all the stages show satisfactory results and e􀀋ectiveness considering formation of charts from analytical text, achieving a commendable overall performance.  \nKeywords: Chart Generation, Natural Language Processing, Information Retrieval, Neural Network, Automated Visualization.  \n∗ fmrashid171045, hjahan171054, ahuzzat171034, rrahul171089, tzakir171032, [fmeem171031](fmeem171031g@bscse.uiu.ac.bd)[g](fmeem171031g@bscse.uiu.ac.bd)[@bscse.uiu.ac.bd](fmeem171031g@bscse.uiu.ac.bd), fsaddam, [swakkhar](swakkharg@cse.uiu.ac.bd)[g](swakkharg@cse.uiu.ac.bd)[@cse.uiu.ac.bd](swakkharg@cse.uiu.ac.bd)  \n1 Introduction  \nIn recent years, advances in Natural Language Processing (NLP) have made huge progress to extract information from natural language texts. Among them a few example tasks are: document summarization [1], title or caption generation from texts, generating textual description of charts [2], named entity recognition [3], etc. There has been several attempts to generate graphs or structural elements from natural language texts or free texts [4, 5, 6, 7] . Scienti􀀌c charts (bar, line, pie, etc.) are visualizations that are often used in communication. However, automated generation of charts from natural language text always has been a challenging task.  \nThere are very few works in the literature addressing the exact problem of scienti􀀌c chart generation from natural language text [8, 9] . In [8], the authors have presented a infographics generation technique from natural language statements. However, their method is limited to single entity generation only. Text2Chart extends it to multiple entity generation and thus can generate more complex charts. Nevertheless, Generative Pre-trained Transformer 3 (GPT-3)[9] has been a recent popular phenomenon in the 􀀌eld of deep learning. OpenAI has designed this third-generation language model that is trained using neural networks. To the best of our knowledge, there has been an attempt to make a simple chart building tool using GPT-3 . As its implementation is not accessible yet, the 􀀌eld of information extraction regarding chart creation can be still considered unexplored to some extent. Moreover, the datasets used in GPT-3 is avery large one and the training is too expensive.  \nIn this paper, we introduce Text2Chart, a multi-staged technique that generates charts from analytical natural language text. Text2Chart works in a combination of three stages. In the 􀀌rst stage, it recognizes x-axis and y-axis entities from the input text. In the second stage, it maps x-axis entities with its corresponding y-axis entities and in the thi","cbCainfIOnZ4Xy8u","https://ap.wps.com/l/cbCainfIOnZ4Xy8u","pdf",1302638,"English","# Introduction\n## Background and related work\n## Problem statement\n## Proposed Text2Chart approach\n## Experimental setup and evaluation","[{\"question\":\"What is Text2Chart and what does it generate?\",\"answer\":\"Text2Chart is a multi-staged chart generator that takes analytical natural language text as input and produces two-dimensional scientific charts.\"},{\"question\":\"How does Text2Chart handle the chart generation process?\",\"answer\":\"It operates in three stages: identifying x- and y-axis entities, mapping x-entities to y-entities, and predicting the best chart type among bar, line, and pie.\"},{\"question\":\"Which models and methods are reported as best-performing for each stage?\",\"answer\":\"The first stage uses BERT embeddings with LSTM for x/y entity labeling, the mapping stage uses Random Forest, and the chart-type prediction stage uses fastText embeddings with LSTM layers.\"}]","Text2Chart - A Multi-Staged Chart Generator from Natural Language Text | PDF",1791839765,7]