[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-663528-105":59,"doc-detail-663528-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","transfeatex-nlp-based-feature-extraction-pipeline","TransFeatEx - NLP-based feature extraction pipeline","","Mobile app stores centralize large volumes of natural-language text, including developer documentation and user reviews, enabling data-driven approaches for automatically extracting app feature sets and related knowledge. With large language models, linguistic methods can be enhanced, and domain knowledge can be better exploited. This paper introduces TransFeatEx, an NLP pipeline that combines a RoBERTa-based model with syntactic and semantic techniques. The pipeline is offered as a customizable standalone service for experimentation and batch processing of large document corpora, with a demo example.",{"@graph":69,"@context":122},[70,84,105],{"@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/transfeatex-nlp-based-feature-extraction-pipeline/663528/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/transfeatex-nlp-based-feature-extraction-pipeline/663528.png","ImageObject",300,407,{"name":92,"@type":93},"Jake","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-10-28",true,{"@type":102,"interactionType":103,"userInteractionCount":8},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is TransFeatEx and what problem does it address?","Question",{"text":112,"@type":113},"TransFeatEx is an NLP-based pipeline for feature extraction. It targets automatic extraction of app features from app-related textual documents such as developer documentation and user reviews.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does TransFeatEx combine models and techniques?",{"text":117,"@type":113},"It combines a RoBERTa-based pretrained model with consolidated syntactic and semantic feature extraction techniques.",{"name":119,"@type":110,"acceptedAnswer":120},"How can the TransFeatEx pipeline be used?",{"text":121,"@type":113},"It is designed as a customizable standalone service that can work as a playground/experimentation tool or be embedded into third-party systems for batch processing large document corpora.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},663528,1793228941,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":8,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":34,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":129,"read_time":143},962084928904,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","TransFeatEx: a NLP pipeline for feature extraction  \nAgustí Gállego1 , Quim Motger1 , Xavier Franch1 and Jordi Marco2  \n1 Department of Service and Information System Engineering, Universitat Politècnica de Catalunya 2 Department of Computer Science, Universitat Politècnica de Catalunya  \nAbstract  \nMobile app stores provide centralized access to a large data set of mobile app related natural language textual data, including developer’s documentation (e.g., descriptions, changelogs) and user-generated data (e.g., user reviews) . Motivated by this context, multiple studies have focused on data-driven elicitation processes for the automatic extraction of the set of features exposed by a catalogue of applications and the inferred, extended knowledge that can be derived from this information. Moreover, with the emerging and generalization of large language models, traditional linguistic-based approaches can be significantly improved by the potential of the knowledge embedded in this kind of models. In this paper, we present TransFeatEx, a NLP-based feature extraction pipeline that combines the use of a RoBERTa-based model with the application of consolidated syntactic and semantic techniques. The pipeline is designed as a customizable, standalone service to be used either as a playground, experimentation tool or as a software component to be embedded into a third-party software system for batch-processing large document corpora. An example of a demo plan is showcased here: [https://youtu.be/gfFyi_i_uTw](https://youtu.be/gfFyi_i_uTw).  \nKeywords  \nfeature extraction, natural language processing, large language models, transformer models, mobile apps  \n1. Introduction  \nIn natural language processing (NLP) and information retrieval, keyword extraction is defined as a text mining process which automatically identifies relevant terms to build condensed representations of text documents [1] . The definition of relevance is tailored by the purpose or application of the keyword extraction process, such as text classification [2], sentiment analysis [3] or document clustering [4] . Whether using statistical or machine/deep learning strategies to support these tasks, the availability of a large, representative document corpus is essential to support their design and implementation, as well as to assess their validity and overall quality. In this sense, app stores have become a popular source of app metadata and app related natural language documents, which can be used as potential sources of descriptors for mobile software applications [5, 6] . As they have become a basic commodity for mobile users world-wide [7], they provide public access to a wide data set of documents, including official developer’s documentation and user reviews. Consequently, they have been used as data sources and development context for multiple software components and tools based on keyword extraction tasks, including app classification [1] and app feature extraction [8] . Concerning the latter,  \nIn: A. Ferrari, B. Penzenstadler, I. Hadar, S. Oyedeji, S. Abualhaija, A. Vogelsang, G. Deshpande, A. Rachmann, J. Gulden, A. Wohlgemuth, A. Hess, S. Fricker, R. Guizzardi, J. Horkoff, A. Perini, A. Susi, O. Karras, A. Moreira, F. Dalpiaz, P. Spoletini, D. Amyot. Joint Proceedings of REFSQ- 2023 Workshops, Doctoral Symposium, Posters & Tools Track, and Journal Early Feedback Track. Co-located with REFSQ 2023 . Barcelona, Catalunya, Spain, April 17, 2023 .  \n © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0) . CWPEURorkroceshopedings http://ceurISSN 1613-ws-0073.org CEUR Workshop Proceedings ([CEUR-WS.org](CEUR-WS.org))  \na comprehensive, accurate representation of the set of features exposed by a set of apps is essential for multiple tasks, [e.g. software](e.g. software) evolution [5], or app recommender systems [9].  \nFeature extraction encompasses NLP techniques which include syntactic","cbCailmk9SD69bDg","https://ap.wps.com/l/cbCailmk9SD69bDg","pdf",1043215,"English","# Abstract\n# 1. Introduction\n# 2. Background","[{\"question\":\"What is TransFeatEx and what problem does it address?\",\"answer\":\"TransFeatEx is an NLP-based pipeline for feature extraction. It targets automatic extraction of app features from app-related textual documents such as developer documentation and user reviews.\"},{\"question\":\"How does TransFeatEx combine models and techniques?\",\"answer\":\"It combines a RoBERTa-based pretrained model with consolidated syntactic and semantic feature extraction techniques.\"},{\"question\":\"How can the TransFeatEx pipeline be used?\",\"answer\":\"It is designed as a customizable standalone service that can work as a playground/experimentation tool or be embedded into third-party systems for batch processing large document corpora.\"}]","TransFeatEx - NLP-based feature extraction pipeline | PDF",18]