Meta tags:
description=Explosion is a software company specializing in developer tools and tailored solutions for Artificial Intelligence and Natural Language Processing. We’re the makers of spaCy, one of the leading open-source libraries for advanced NLP.;

Headings (most frequently used words):

the, ai, and, for, in, with, nlp, to, of, 2024, prodigy, 2025, spacy, ellf, pydata, how, v0, your, 2026, building, keynote, applied, de, ki, open, source, 18, age, generative, future, german, career, pdfs, pdf, 0nov, v1, coding, layout, web, us, llm, pipelines, agentic, development, using, annotation, aipycon, und, not, natural, language, processing, code, from, aidotai, agent, developer, their, chat, vibe, is, it, based, conquering, document, understanding, beyond, plain, python, classification, reality, end, london, rhetoric, uk, podcast, 24, what, history, can, teach, about, llms, warum, spatial, entities, newsletter, evaluate, optimize, templatesoct, 29, our, new, tool, atomic, multimodal, corpora, microtask, local, annotatorshotti, vázquez, jokipohja, kalliokoski, paakki, suviranta, hiippala, ultimate, guide, optimizing, workflows, ireland, proof, strategies, banking, financeecondat, feminist, lan, partypycon, zwischen, freiheit, kontrolle, revolution, will, be, monopolizeddata, unplugged, mastering, spacydéborah, mesquita, duygu, altinok, packt, publishing, identify, emergency, department, patients, incidental, lung, nodules, requiring, follow, upmoore, socrates, hesami, denkewicz, cavallo, venkatesh, taylor, cracking, start, aiwelcome, jungle, ready, structured, data, deep, dive, 25, 16, 0oct, 22, accelerate, ux, tools, humans, agents, happy, 10th, anniversary, quick, ines, mattpy4ai, nlppycon, style, tips, less, experienced, developers, reshaping, skillsconnect, professional, 2graphrag, streamlining, graph, rag, high, efficiency, effectivenesszhao, zhu, guo, he, li, textpycon, advocate, modular, 12mar, prozessvisualisierung, mit, generativer, im, praxistestix, magazin, heise, best, way, ocr, tutorials, digital, humanities, beginner, advancedguan, wang, xiaoquan, kong, 17, uottawa, at, legallens, transformer, experimentsmeghdadi, inkpen, an, prediction, problem, introducing, missing, piece, assistants, nlpbuild, taking, back, control, developmentfeminist, century, immigration, parliamentgennaro, vissens, thornewill, von, essen, ravalde, egan, dave, dable, facini, ricoreca, rich, cooking, recipe, schemaventirozos, jacob, romero, alrdahi, clinch, batista, navarro, sovereign, systems, instead, black, box, solutionsit, daily, trends, 2025talkpython, keyword, extraction, aspect, sinhala, english, mixed, contentrizvi, navojith, adhikari, senevirathna, kasthurirathna, abeywardhana, love, without, sound, helps, music, industry, recover, millions, revenue, artists, 0feb, streaming, pyladies, entrepreneurs, developmentpyladiescon, distill, surpass, performanceinfoq, magazine, virtual, engineer, build, own, humanspydata, pycon, yerevan, show, skillspymc, labs, vanishing, gradients, rightwing, has, risen, sharply, parliamentthe, guardian, engineering, human, aligned, evaluation, workflow, dspy, textpydata, fireside, enterprise, innovationpycon, ohne, ketten, gegen, big, tech, gewinnen, kannunmute, künstliche, intelligenz, technologie, der, zukunft, die, karten, neu, mischtheise, woche, dashboard, plugin, recognising, non, named, literary, texts, novel, classifierkababgi, grisot, pennino, herrmann, 6nov, 1nov, serverless, custom, modal, project, topics, category, tasks, authors,

Text of the page (most frequently used words):
and (114), the (82), for (53), with (35), nlp (33), 2025 (32), talk (26), 2026 (24), spacy (22), 2024 (21), prodigy (19), blog (19), this (19), ines (19), how (17), #annotation (14), open (14), source (14), about (14), new (14), using (14), what (13), build (13), oct (12), data (12), model (12), llms (11), you (11), interview (11), your (11), #coding (11), ellf (10), solutions (10), pdfs (10), paper (10), building (10), software (9), our (9), can (9), systems (9), are (9), agents (9), use (9), end (9), developer (8), german (8), web (8), future (8), models (8), development (8), text (8), code (8), tools (7), language (7), from (7), more (7), dec (7), pycon (7), apr (7), pydata (7), pipelines (7), based (7), tasks (7), custom (6), extraction (6), nov (6), jan (6), developers (6), jun (6), modular (6), document (6), understanding (6), that (6), feb (6), powered (6), workflows (6), instead (6), video (6), career (6), generative (6), explosion (5), case (5), processing (5), post (5), layout (5), mar (5), create (5), llm (5), universe (5), classification (5), their (5), take (5), tool (5), into (5), components (5), featuring (5), transformer (5), applied (5), book (5), finance (4), natural (4), support (4), entities (4), release (4), history (4), teach (4), keynote (4), discussion (4), approach (4), python (4), beyond (4), human (4), may (4), skills (4), own (4), shows (4), agentic (4), platform (4), all (4), ner (4), industry (4), them (4), problems (4), assistant (4), legal (3), humanities (3), tailored (3), view (3), past (3), join (3), projects (3), show (3), modal (3), documents (3), add (3), study (3), prediction (3), named (3), spatial (3), learning (3), plugin (3), look (3), big (3), panel (3), presents (3), robust (3), state (3), art (3), london (3), workflow (3), evaluation (3), has (3), agent (3), why (3), gives (3), virtual (3), practical (3), real (3), world (3), pdf (3), matt (3), will (3), span (3), article (3), pipeline (3), solving (3), small (3), private (3), like (3), not (3), age (3), entity (3), proof (3), out (3), less (3), have (3), years (3), structured (3), generation (3), consulting (3), computer (2), vision (2), media (2), biomedical (2), strategy (2), topics (2), events (2), specializing (2), one (2), advanced (2), issues (2), mailing (2), list (2), receive (2), updates (2), posts (2), newsletter (2), fully (2), information (2), infrastructure (2), process (2), tables (2), convert (2), non (2), deep (2), dashboard (2), annotations (2), now (2), takes (2), means (2), regulation (2), artificial (2), intelligence (2), impact (2), heise (2), und (2), warum (2), podcast (2), tech (2), alexander (2), reality (2), chat (2), awesome (2), ecosystem (2), conquering (2), plain (2), loop (2), dspy (2), aligned (2), guide (2), analysis (2), guardian (2), automated (2), training (2), rhetoric (2), parliament (2), they (2), jul (2), apis (2), back (2), control (2), these (2), important (2), than (2), ever (2), humans (2), help (2), presentation (2), infoq (2), montani (2), applications (2), smaller (2), faster (2), performance (2), multi (2), page (2), business (2), works (2), features (2), fixes (2), things (2), cet (2), learn (2), love (2), without (2), sound (2), music (2), keyword (2), english (2), embeddings (2), which (2), richard (2), black (2), box (2), two (2), annotator (2), romero (2), annotated (2), roberta (2), base (2), short (2), work (2), house (2), feminist (2), could (2), learnings (2), apply (2), built (2), powerful (2), fast (2), vibe (2), claude (2), missing (2), develop (2), assistants (2), dotai (2), been (2), first (2), experienced (2), traditional (2), way (2), ocr (2), pii (2), anonymization (2), advocate (2), rag (2), professional (2), over (2), tips (2), inspired (2), vibes (2), apps (2), cross (2), cases (2), lung (2), then (2), follow (2), duygu (2), altinok (2), publishing (2), should (2), larger (2), hacking (2), banking (2), supporting (2), atomic (2), project (2), templates (2), select (2), recognition (2), image (2), machine (2), 2016, imprint, studies, home, navigation, company, makers, leading, libraries, idea, little, gpu, setup, required, serverless, word, tabular, pandas, dataframe, present, call, nnse, historical, corpus, swiss, novels, conjunction, bert, kababgi, grisot, pennino, herrmann, recognising, literary, texts, novel, classifier, adds, application, managing, analytics, progress, available, early, beta, testing, woche, künstliche, intelligenz, technologie, der, zukunft, die, karten, neu, mischt, ethics, sustainable, unmute, ohne, ketten, gegen, gewinnen, kann, hendorf, beck, walid, mehanna, fireside, enterprise, innovation, demonstrates, developing, evaluating, task, specific, metrics, optimization, generic, measures, engineering, depth, collaboration, university, college, semi, rightwing, risen, sharply, people, top, game, doing, episode, sharing, pymc, labs, vanishing, gradients, bootstrapped, mean, yerevan, series, overview, its, philosophy, engineer, her, dev, summit, provided, audience, latest, distilling, knowledge, magazine, distill, surpass, single, challenges, starting, cheuk, ting, tereza, iofciu, anwesha, das, una, galyeva, pyladiescon, pyladies, entrepreneurs, author, core, library, develops, bugs, while, chatting, every, thursday, 2pm, friday, 11am, streaming, there, lot, another, groundbreaking, technology, editing, during, translations, javascript, innovative, law, firms, royalty, negotiations, helps, recover, millions, revenue, artists, performed, hybrid, comprising, fine, tuned, finbert, keybert, yake, embedrank, results, combined, accuracy, rizvi, navojith, adhikari, senevirathna, kasthurirathna, abeywardhana, aspect, sinhala, mixed, content, michael, kennedy, calvin, hendryx, parker, gina, häußge, campbell, talkpython, trends, role, daily, sovereign, consists, sections, firstly, utilized, customized, interface, complete, ventirozos, jacob, alrdahi, clinch, batista, navarro, ricoreca, rich, cooking, recipe, schema, snippets, trained, classifiers, each, consisting, textcat, categorisation, component, gennaro, vissens, thornewill, von, essen, ravalde, egan, dave, dable, facini, century, immigration, unconference, current, focus, empowering, again, taking, aug, plugs, already, codex, github, copilot, pieces, introducing, piece, problem, utilizes, configured, transition, parser, deberta, selected, main, architecture, meghdadi, inkpen, uottawa, legallens, experiments, pages, longer, collections, images, chinese, beginners, practitioners, covering, techniques, leverage, various, guan, wang, xiaoquan, kong, beginner, tutorial, wjb, mattingly, package, docling, tutorials, digital, best, nils, durner, visualizing, technical, processes, presidio, magazin, prozessvisualisierung, mit, generativer, praxistest, context, index, docs, hype, around, many, led, believe, solution, everything, communicate, nuances, better, easier, cheaper, employ, extract, occurrence, chunk, relations, zhao, zhu, guo, 2graphrag, streamlining, graph, high, efficiency, effectiveness, professionals, connect, reshaping, getting, good, prompts, steer, towards, shares, some, lessons, engineers, learned, bigger, style, impromptu, conference, sunny, pavia, py4ai, quick, sep, exactly, ago, today, officially, founded, much, happened, since, got, witness, field, evolve, become, mainstream, hypes, come, thanks, happy, 10th, anniversary, long, time, visual, saas, changing, need, just, well, operating, making, gael, varoquaux, scikit, steeve, morin, zml, accelerate, demand, deployment, wheels, converting, similar, ready, dive, job, hunters, cultivate, welcome, jungle, cracking, start, reports, were, raters, stepwise, excluded, prior, known, malignancy, determined, presence, nodule, categorized, any, recommended, was, developed, large, moore, socrates, hesami, denkewicz, cavallo, venkatesh, taylor, identify, emergency, department, patients, incidental, nodules, requiring, empowered, integrate, déborah, mesquita, packt, mastering, envision, practice, heading, further, era, obscured, behind, controlled, monopolies, unplugged, zwischen, freiheit, kontrolle, revolution, monopolized, three, days, workshops, creating, connecting, locally, workshop, session, lan, party, modern, mindset, focusing, economics, econdat, strategies, transformed, itself, ireland, collects, advice, efficient, break, down, actionable, steps, make, most, automation, assistance, ultimate, optimizing, needed, effort, repurpose, existing, commercial, enhance, additional, combining, validating, access, hotti, vázquez, jokipohja, kalliokoski, paakki, suviranta, hiippala, multimodal, corpora, microtask, local, annotators, methodology, design, reliable, composable, prompt, superpowers, execute, centric, set, adapted, relying, get, clear, picture, replace, costly, calls, evaluate, optimize, walter, henry, vinit, ravishankar, vincent, warmerdam, victoria, slocum, sofie, van, landeghem, ryan, wesslen, hudson, rehan, ahmed, raphael, mitsch, philip, vollet, peter, baumgartner, paul, leary, mccann, matthew, honnibal, magdalena, anioł, madeesh, kannan, miranda, kabir, khan, india, kerle, helena, steckmeister, edward, schmuhl, daniël, kok, damian, chung, fan, tsai, basile, dura, ákos, kádár, adriane, boyd, authors, weak, supervision, tokenization, categorization, rule, matching, retrieval, augmented, relation, question, answering, part, speech, tagging, optical, character, object, detection, lemmatization, segmentation, linking, vectors, distillation, dependency, parsing, coreference, resolution, category, thinc, filters, builds,

Text of the page (random words):
udy topics llms nlp strategy annotation biomedical finance media legal humanities computer vision category blog release universe talk interview video paper book tasks select code generation coreference resolution dependency parsing distillation embeddings vectors entity linking evaluation image classification image segmentation layout analysis lemmatization named entity recognition object detection optical character recognition ocr part of speech tagging pii anonymization question answering relation extraction retrieval augmented generation rag rule based matching span categorization text classification text generation tokenization weak supervision authors select adriane boyd ákos kádár basile dura chung fan tsai damian romero daniël de kok duygu altinok edward schmuhl helena steckmeister india kerle ines montani kabir khan lj miranda madeesh kannan magdalena anioł matthew honnibal paul o leary mccann peter baumgartner philip vollet raphael mitsch rehan ahmed richard hudson ryan wesslen sofie van landeghem victoria slocum vincent d warmerdam vinit ravishankar walter henry newsletter join our mailing list to receive updates about new blog posts and projects view past issues evaluate and optimize llm pipelines with ellf instead of relying on vibes get a clear picture of what works and replace costly llm calls with smaller faster and private components release oct 26 2026 ellf templates oct 29 2026 project templates for end to end nlp workflows set up and adapted to your use case by your coding agent ellf our new tool for agentic nlp development ellf gives your coding assistant like claude code superpowers for solving nlp problems and a platform to execute data centric projects automated annotation and more release oct 5 2026 atomic nlp an applied nlp methodology inspired by atomic design building reliable language understanding systems out of small composable components instead of one big model and a prompt blog jun 24 2026 building multimodal corpora using microtask pipelines and local annotators hotti vázquez jokipohja kalliokoski paakki suviranta hiippala 2026 to create the infrastructure needed for supporting this effort we repurpose an existing commercial annotation tool prodigy which we then enhance with additional components for combining the annotation tasks into pipelines cross validating the annotations and supporting annotator access to tasks paper may 11 2026 the ultimate guide to optimizing annotation workflows this blog post collects tips and advice for how to build efficient human in the loop data development workflows break down business problems into actionable annotation steps and make the most of automation and model assistance blog feb 24 2026 building ai with ai pycon ireland keynote ai powered coding assistants have transformed the way we build software and ai itself in this talk ines shows why we should use llms to build systems instead of as systems and why code is more important than ever not less talk nov 15 2025 applied nlp in the age of generative ai future proof strategies for banking and finance econdat keynote a modern approach and mindset for building future proof nlp pipelines in house focusing on use cases from banking finance and economics talk jun 5 2025 feminist ai lan party pycon de pydata three days of workshops hacking creating publishing and connecting locally featuring a data development workshop with prodigy and a session on hacking llms talk apr 23 2025 ki zwischen freiheit und kontrolle the ai revolution will not be monopolized data unplugged german how should we envision the use of ai in practice and are we heading further into a black box era with larger and larger models obscured behind apis controlled by big tech monopolies talk apr 10 2025 mastering spacy déborah mesquita duygu altinok packt publishing 2025 build structured nlp solutions with custom components and models powered by llms by end of the book you will be empowered to build robust nlp pipelines and integrate them with web applications to build end to end solutions book feb 14 2025 using natural language processing to identify emergency department patients with incidental lung nodules requiring follow up moore socrates hesami denkewicz cavallo venkatesh taylor 2025 ct reports were annotated by md raters using prodigy software to develop a stepwise nlp pipeline that first excluded prior or known malignancy determined the presence of a lung nodule and then categorized any recommended follow up nlp was developed using a roberta large language model on the spacy platform paper jan 17 2025 cracking the code how to start a career in ai welcome to the jungle short video interview with ines about the 4 skills job hunters can cultivate for a career in artificial intelligence interview dec 17 2024 from pdfs to ai ready structured data a deep dive this blog post presents a new modular workflow for converting pdfs and similar documents to structured data and shows you how to build end to end document understanding and information extraction pipelines for industry use cases blog dec 2 2024 prodigy pdf v0 4 0 nov 25 2024 add text based span annotation for pdfs prodigy v1 16 0 oct 22 2024 modal plugin for on demand deployment cross platform wheels and ui fixes accelerate your career with open source ai dotai panel discussion about making a career out of open source software featuring gael varoquaux scikit learn steeve morin zml and ines talk oct 17 2024 agent ux building developer tools for humans and their coding agents for a long time visual saas apps have been the go to for professional tools with coding agents this is changing and the apps we build now need to work just as well for the agents operating them blog oct 21 2026 happy 10th anniversary exactly 10 years ago today we officially founded explosion so much has happened since and we got to witness the field evolve ai become mainstream and hypes come and go thanks to all of you for your support over the past 10 years and beyond blog sep 5 2026 a quick chat with ines matt py4ai impromptu video interview on what inspired our talk and the conference vibes in sunny pavia interview jun 13 2026 vibe nlp for applied nlp pycon de pydata what if we could take learnings from ai powered coding agents and apply them to solving real world nlp problems in this talk i ll show how we ve built a powerful virtual nlp assistant to help developers create practical and modular solutions that are small fast and fully data private talk apr 16 2026 style tips for less experienced developers coding with ai getting good performance out of llm coding is less about prompts or agents and more about the code you steer the model towards matt shares some lessons software engineers have learned over the years about building bigger things blog feb 5 2026 how ai is reshaping it skills connect professional german article featuring ines take on the impact of ai on future proof skills for it professionals interview jul 11 2025 e 2graphrag streamlining graph based rag for high efficiency and effectiveness zhao zhu guo he li 2025 instead of using llms for entity extraction we employ the traditional nlp tool spacy to extract entities and use their co occurrence in a chunk as relations paper may 30 2025 conquering pdfs document understanding beyond plain text pycon de pydata in this talk ines presents a new and modular approach for building robust document understanding systems using state of the art models and the awesome python ecosystem talk apr 23 2025 how to advocate for modular nlp in the age of generative ai with all the hype around generative ai many are led to believe it s the solution to everything so how can you as a developer communicate the nuances and advocate for new and modular solutions that are better easier and cheaper blog mar 31 2025 spacy layout v0 0 12 mar 8 2025 support processing pdfs with context add document index tables and more docs prozessvisualisierung mit generativer ki im praxistest ix magazin heise german article by nils durner on visualizing technical processes with generative ai featuring spacy and presidio for pii anonymization universe feb 10 2025 best way to ocr a pdf in python python tutorials for digital humanities tutorial by wjb mattingly on how to use the new spacy layout package and docling to convert pdfs to text universe jan 14 2025 spacy natural language processing from beginner to advanced guan wang xiaoquan kong 2024 the first chinese language book on spacy for beginners and experienced practitioners covering traditional nlp techniques and how to leverage llms for various nlp tasks book dec 16 2024 prodigy v1 17 0 nov 18 2024 pages ui for multi page tasks like longer documents pdfs or collections of images uottawa at legallens 2024 transformer based classification experiments meghdadi inkpen 2024 our training utilizes the spacy pipeline configured with a transformer model and a transition based parser for ner tasks the deberta v3 base model has been selected for the main transformer architecture paper oct 28 2024 reality is not an end to end prediction problem applied nlp in the age of generative ai dotai talk oct 17 2024 introducing ellf the missing piece for building nlp with coding assistants ellf is our new tool that plugs into the coding assistant you already use like claude code codex or github copilot and gives it the missing pieces to develop custom ai systems blog oct 14 2026 vibe nlp for applied nlp build with ai what if we could take learnings from ai powered coding agents and apply them to solving real world nlp problems in this talk ines shows you these new agentic workflows and how we ve built a powerful virtual assistant to create practical solutions that are small fast and data private talk aug 10 2026 taking back control of your ai development feminist ai pydata london short unconference presentation by ines on the current focus of our work empowering developers to build ai in house again talk jun 6 2026 a century of immigration rhetoric in the uk parliament gennaro vissens thornewill von essen ravalde egan dave dable facini 2026 with all annotated snippets we trained two transformer based classifiers each using a spacy pipeline consisting of a roberta base transformer model and spacy s textcat text categorisation component paper mar 10 2026 ricoreca rich cooking recipe annotation schema ventirozos jacob romero alrdahi clinch batista navarro 2026 the annotation process consists of two sections firstly the annotator utilized a customized prodigy interface to complete the ner and rc annotation tasks paper jan 12 2026 sovereign ai systems instead of black box solutions it daily german article featuring ines take on ai in industry the role of open source and using generative ai to create systems interview jun 17 2025 developer trends in 2025 talkpython podcast discussion with michael kennedy calvin hendryx parker gina häußge richard campbell and ines interview may 5 2025 keyword extraction and aspect classification in sinhala english and code mixed content rizvi navojith adhikari senevirathna kasthurirathna abeywardhana 2025 keyword extraction in english is performed with a hybrid approach comprising a fine tuned spacy ner model finbert based keybert embeddings yake and embedrank which results in a combined accuracy of 91 2 paper apr 14 2025 how love without sound helps the music industry recover millions in revenue for artists with nlp spacy and prodigy a case study on love without sound s innovative ai powered tools for the music industry and law firms specializing in royalty negotiations blog mar 24 2025 prodigy v1 18 0 feb 24 2025 text editing during ner and span annotation custom translations and more javascript features what the history of the web can teach us about the future of ai how will ai development look in the future there is a lot we can learn from another groundbreaking technology the web this blog post takes a look at what the history of the web can teach us and what this means for developers models open source and regulation blog jan 27 2025 streaming spacy join spacy author and core developer matt as he works on the library develops features and fixes bugs while chatting about all things nlp and open source every thursday at 2pm cet and friday at 11am cet video jan 9 2025 pyladies entrepreneurs and career development pyladiescon panel discussion about career challenges and starting your own business with cheuk ting ho tereza iofciu anwesha das una galyeva and ines talk dec 7 2024 prodigy pdf v0 3 0 nov 18 2024 support multi page pdfs in a single view distill your llms and surpass their performance infoq magazine in her presentation at infoq dev summit ines montani provided the audience with practical solutions for using the latest state of the art models in real world applications and distilling their knowledge into smaller and faster components universe oct 26 2024 ellf your virtual nlp engineer in this new video series ines gives you an overview of our new tool and platform ellf its philosophy and how to use it to build your own custom nlp pipelines with the help of agents video oct 10 2026 build to own ai agentic development for humans pydata pycon yerevan keynote instead of using llm apis we can take back control and build our own systems bootstrapped by agents in this talk ines shows you these new agentic workflows what they mean for developer tools and why code and open source are more important than ever talk jul 24 2026 show us your agent skills pymc labs vanishing gradients what are people at the top of the game building with ai agents and how are they doing it in this episode 6 developers are sharing their workflows interview may 21 2026 how rightwing rhetoric has risen sharply in the uk parliament the guardian in depth analysis by the guardian in collaboration with university college london powered by prodigy for semi automated data annotation and spacy for classification model training and prediction universe feb 25 2026 engineering a human aligned llm evaluation workflow with prodigy and dspy this post demonstrates a human in the loop workflow for developing and evaluating llms using prodigy and dspy to create task specific human aligned metrics that guide model optimization beyond generic evaluation measures blog dec 1 2025 conquering pdfs document understanding beyond plain text pydata london in this talk ines presents a new and modular approach for building robust document understanding systems using state of the art models and the awesome python ecosystem talk jun 7 2025 ai in reality fireside chat enterprise ai open source innovation pycon de pydata panel discussion with alexander cs hendorf dr alexander beck walid mehanna and ines talk apr 24 2025 ki ohne ketten warum open source gegen big tech gewinnen kann unmute it podcast german interview with ines on open source llms ethics and sustainable ai development interview apr 13 2025 künstliche intelligenz technologie der zukunft und warum open source die...