[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-517924-105":59,"doc-detail-517924-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","a-multilingual-information-extraction-pipeline-for-investigative-journalism-research","A Multilingual Information Extraction Pipeline for Investigative Journalism - Research","","Advanced information extraction pipeline for investigative journalism processes very large collections of unstructured text to quickly surface potential stories. Built as an input processor for New/s/leak 2.0, it supports multi-language document sets up to 40 languages and extracts full text, metadata, and entities across diverse file formats. The approach combines entity extraction with co-occurrence analysis and assembles state-of-the-art NLP components for temporal entities, named entities, key terms, patterns, and dictionaries.",{"@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/a-multilingual-information-extraction-pipeline-for-investigative-journalism-research/517924/",{"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/a-multilingual-information-extraction-pipeline-for-investigative-journalism-research/517924.png","ImageObject",300,407,{"name":92,"@type":93},"Patrick","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-16","2026-10-07",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the pipeline address in investigative journalism?","Question",{"text":112,"@type":113},"It automatically processes very large collections of unstructured text to help journalists discover potential stories by extracting entities and analyzing their co-occurrence.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does New/s/leak 2.0 handle multilingual data?",{"text":117,"@type":113},"It includes automatic language detection and supports information extraction across 40 languages, enabling extraction from multilingual document sets for cross-country collaboration.",{"name":119,"@type":110,"acceptedAnswer":120},"What kinds of information does the system extract and from which file formats?",{"text":121,"@type":113},"It extracts full-text, metadata, and entities, including temporal entities, named entities, key terms, regex-based patterns such as URLs and emails, and user-defined dictionaries; it also supports multiple file formats using data wrangling for scalability.","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},517924,1791471203,{"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":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":29,"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":143,"read_time":144,"preview_page_count":19,"preview_urls":145},549758146520,"https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470","A Multilingual Information Extraction Pipeline for Investigative Journalism  \nGregor Wiedemann Seid Muhie Yimam Chris Biemann  \nLanguage Technology Group  \nDepartment of Informatics  \nUniversitt Hamburg, Germany  \nfgwiedemann, yimam, biemanng@informatik.uni-hamburg .de  \nAbstract  \nWe introduce an advanced information extraction pipeline to automatically process very large collections of unstructured textual data for the purpose of investigative journalism. The pipeline serves as a new input processor for the upcoming major release of our New/s/leak 2.0 software, which we develop in cooperation with a large German news organization. The use case is that journalists receive a large collection of ﬁles up to several Gigabytes containing unknown contents. Collections may originate either from ofﬁcial disclosures of documents, e.g. Freedom of Information Act requests, or unofﬁcial data leaks. Our software prepares a visually-aided exploration of the collection to quickly learn about potential stories contained in the data. It is based on the automatic extraction of entities and their co-occurrence in documents. In contrast to comparable projects, we focus on the following three major requirements particularly serving the use case of investigative journalism in cross-border collaborations: 1) composition of multiple state-of-the-art NLP tools for entity extraction, 2) support of multi-lingual document sets up to 40 languages, 3) fast and easyto-use extraction of full-text, metadata and entities from various ﬁle formats.  \n1 Support Investigative Journalism  \nJournalists usually build up their stories around entities of interest such as persons, organizations, companies, events, and locations in combination with the complex relations they have. This is especially true for investigative journalism which, in the digital age, more and more is confronted to ﬁnd such relations between entities in large, unstructured and heterogeneous data sources.  \nUsually, this data is buried in unstructured texts, for instance from scanned and OCR-ed documents, letter correspondences, emails or protocols. Sources typically range from 1) ofﬁcial disclosures of administrative and business documents,  \n2) court-ordered revelation of internal communication, 3) answers to requests based on Freedom of Information (FoI) acts, and 4) unofﬁcial leaks of conﬁdential information. Well-known examples of such disclosed or leaked datasets are the Enron email dataset (Keila and Skillicorn, 2005) or the Panama Papers (O'Donovan et al., 2016) .  \nTo support investigative journalism in their work, we have developed New/s/leak (Yimam et al., 2016), a software implemented by experts from natural language processing and visualization in computer science in cooperation with journalists from Der Spiegel, a large German news organization. Due to its successful application in the investigative research as well as continued feedback from academia, we further extend the functionality of New/s/leak, which now incorporates better pre-processing, information extraction and deployment features. The new version New/s/leak 2.0 serves four central requirements that have not been addressed by the ﬁrst version or other existing solutions for investigative and forensic text analysis:  \nImproved NLP processing: We use stable and robust state-of-the-art natural language processing (NLP) to automatically extract valuable information for journalistic research. Our pipeline combines extraction of temporal entities, named entities, key-terms, regular expression patterns (e.g. URLs, emails, phone numbers) and user-deﬁned dictionaries.  \nMultilingualism: Many tools only work for English documents or a few other `big languages'. In the new version, our tool allows for automatic language detection and information extraction in 40 different languages. Support of multilingual collections and documents is speciﬁcally useful to foster cross-country collaboration in journalism. Multiple ﬁle formats: Ext","cbCaill9Rq0BuqMg","https://ap.wps.com/l/cbCaill9Rq0BuqMg","pdf",861774,"English","# Abstract\n# 1 Support Investigative Journalism\n# 2 Related Work","[{\"question\":\"What problem does the pipeline address in investigative journalism?\",\"answer\":\"It automatically processes very large collections of unstructured text to help journalists discover potential stories by extracting entities and analyzing their co-occurrence.\"},{\"question\":\"How does New/s/leak 2.0 handle multilingual data?\",\"answer\":\"It includes automatic language detection and supports information extraction across 40 languages, enabling extraction from multilingual document sets for cross-country collaboration.\"},{\"question\":\"What kinds of information does the system extract and from which file formats?\",\"answer\":\"It extracts full-text, metadata, and entities, including temporal entities, named entities, key terms, regex-based patterns such as URLs and emails, and user-defined dictionaries; it also supports multiple file formats using data wrangling for scalability.\"}]","A Multilingual Information Extraction Pipeline for Investigative Journalism - Research | PDF",1791348838,15,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/a63629dca9ab1135c626dfedd8fa5be5.webp",983,1390,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/56a4284b15bd527ded2d47e8865fc834.webp",982,1388,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/ca1ef1d015ad568aa3a951d433ab0689.webp",981,1387,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/e5b0bb66ba9d9e08d219eff0e0590d7e.webp",980,1385]