recentpopularlog in

kintopp : analysis   359

« earlier  
Drag-and-drop data analytics | MIT News
In the Iron Man movies, Tony Stark uses a holographic computer to project 3-D data into thin air, manipulate them with his hands, and find fixes to his superhero troubles. via Pocket
analysis  deep  interactive  ml  tools 
12 days ago by kintopp
Nicolas Gonthier
Je suis doctorant au sein de l’équipe IMAGES du LTCI de Télécom ParisTech. Mes intérêts de recherche sont l’apprentissage profond (Deep Learning) appliqué à l’histoire de l’art et aux données historiques en générale.
art  arthistory  france  images  history  analysis  deep 
4 weeks ago by kintopp
VISART IV
Paper submission is now open - please use this site to submit your paper! via Pocket
analysis  art  arthistory  cfp  conference  germany  images  ml  recognition 
4 weeks ago by kintopp
Postdoc Job – Apply Now!
We’re hiring a postdoc in image processing and classification! Job Description DataLab is inviting applications for a full-time postdoctoral scholar in image processing and classification beginning Summer/Fall 2019. via Pocket
analysis  arthistory  deep  images  jobs 
4 weeks ago by kintopp
SoNAR (IDH) – Interfaces to Data for Historical Social Network Analysis and Research
Our mission is to advance the use of human languages by machines and to create and improve IT-solutions that benefit from language use. Key areas of activity include text analytics, machine translation, human-robot interaction and digital content creation. via Pocket
analysis  germany  history  networks  text 
4 weeks ago by kintopp
Evaluating the Practices and Legacy of the Enlightenment on 19th Century Print Culture | ARTFL Project Research Blog
While the ARTFL Project had built text alignment packages in the past, this system was not built for very large-scale comparisons -- 100,000+ document ranges. As such, we wanted to create a new software package that could retain the strengths of PhiloLine while addressing the problem of scalability. via Pocket
analysis  artfl  paper  text  tools 
5 weeks ago by kintopp
PROVIDEDH – PROgressive VIsual DEcision-Making in Digital Humanities
The PROgressive VIsual DEcision-Making in Digital Humanities (PROVIDEDH) project is a three-year project funded within the CHIST-ERA call 2016 for the topic “Visual Analytics for Decision Making under Uncertainty – VADMU. via Pocket
analysis  datasets  humanities  visualization 
5 weeks ago by kintopp
A Word is Worth a Thousand Vectors | Stitch Fix Technology – Multithreaded
Standard natural language processing (NLP) is a messy and difficult affair. It requires teaching a computer about English-specific word ambiguities as well as the hierarchical, sparse nature of words in sentences. At Stitch Fix, word vectors help computers learn from the raw text in customer notes. via Pocket
analysis  learn  ml  nlp  text 
5 weeks ago by kintopp
gepris.dfg.de
iART: Ein interaktives Analyse- und Retrieval-Tool zur Unterstützung von bildorientierten Forschungsprozessen
analysis  art  arthistory  germany  images  ml  munich  neural 
5 weeks ago by kintopp
fortext.net
Was macht forTEXT? Im Projekt forTEXT erarbeiten wir eine digitale Forschungsumgebung für Geisteswissenschaftler*innen. via Pocket
analysis  germany  software  text  visualization 
7 weeks ago by kintopp
Natural Language Processing is Fun! – Adam Geitgey – Medium
This article is part of an on-going series on NLP: Part 1, Part 2, Part 3. You can also read a reader-translated version of this article in 普通话. via Pocket
analysis  books  learn  nlp  text 
9 weeks ago by kintopp
Interpretable Machine Learning
Machine learning has great potential for improving products, processes and research. But computers usually do not explain their predictions which is a barrier to the adoption of machine learning. This book is about making machine learning models and their decisions interpretable. via Pocket
analysis  deep  methodology  ml 
9 weeks ago by kintopp
A Scalable Handwritten Text Recognition System
Many studies on (Offline) Handwritten Text Recognition (HTR) systems have focused on building state-of-the-art models for line recognition on small corpora. However, adding HTR capability to a large scale multilingual OCR system poses new challenges. This paper addresses three problems in building such systems: data, efficiency, and integration. Firstly, one of the biggest challenges is obtaining sufficient amounts of high quality training data. We address the problem by using online handwriting data collected for a large scale production online handwriting recognition system. We describe our image data generation pipeline and study how online data can be used to build HTR models. We show that the data improve the models significantly under the condition where only a small number of real images is available, which is usually the case for HTR models. It enables us to support a new script at substantially lower cost. Secondly, we propose a line recognition model based on neural networks without recurrent connections. The model achieves a comparable accuracy with LSTM-based models while allowing for better parallelism in training and inference. Finally, we present a simple way to integrate HTR models into an OCR system. These constitute a solution to bring HTR capability into a large scale OCR system.
analysis  handwriting  ocr  tools 
9 weeks ago by kintopp
InFoDiTex DiscourseLab Corpus Contest
Das InFoDiTex (Universität Heidelberg) veranstaltet in Zusammenarbeit mit dem Discourse Lab (Technische Universität Darmstadt) einen „Interdisziplinären Corpus Contest“ mit dem Ziel, Disziplinen zusammenzubringen, die mit „Text als Quelle“ arbeiten, und mit ihnen Kooperationspotentiale zw via Pocket
analysis  datasets  germany  hackathon  nlp  text 
9 weeks ago by kintopp
On the perceived complexity of literature. A response to Nan Z. Da « CA: Journal of Cultural Analytics
At the center of Nan Z. Da's article is the claim that quantitative methods cannot produce any useful insights with respect to literary texts: via Pocket
analysis  debates  methodology  text 
9 weeks ago by kintopp
Content Based Image Recognition for Early Modern Images
Archv is a tool to search an imageset to find the best matches with your seed image. This page allows you to upload and compare an image of your choice with either the English Broadside Ballad Archive imageset or a curated image set from the British Library's Flickr. via Pocket
analysis  history  images  recognition  tools 
9 weeks ago by kintopp
Automated Authorship Verification: Did We Really Write Those Blogs We Said We Wrote?—Wolfram Blog
I wrote a blog post about the disputed Federalist Papers. These were the 12 essays (out of a total of 85) with authorship claimed by both Alexander Hamilton and James Madison. via Pocket
analysis  text  wolfram 
12 weeks ago by kintopp
Confabulation in the humanities - Matthew Lincoln, PhD
It’s a tale as old as the “digital humanities” itself: skeptics rightly asking whether or not we are actually learning anything new by using quantitative approaches to historical questions. This is a legitimate question. via Pocket
analysis  methodology 
may 2019 by kintopp
Nineteen
Visually explore your data
analysis  datasets  tools  visualization 
may 2019 by kintopp
Computational Literary Studies: A Critical Inquiry Online Forum
Beginning on 1 April, this Critical Inquiry online forum will feature responses to and discussion about Nan Z. Da’s “The Computational Case against Computational Literary Studies.”
analysis  chicago  debates  dh  forum  methodology  text  usa 
may 2019 by kintopp
LOD Laundromat
The LOD Laundromat provides access to all Linked Open Data (LOD) in the world. It does this by crawling the LOD cloud, and converting all its contents in a standards-compliant way (gzipped N-Triples), removing all data stains such as syntax errors, duplicates, and blank nodes. via Pocket
analysis  api  data  datasets  linkeddata  metadata  quality  sparql  tools 
may 2019 by kintopp
Detecting Footnotes in 32 million pages of ECCO « CA: Journal of Cultural Analytics
Clusters: Data, Image Article DOI: 10.22148/16.029 Dataverse DOI: 10.7910/DVN/FMZYFP Journal ISSN: 2371-4549 Cite: Sherif Abuelwafa, Sara Zhalepour, Ehsan Arabnejad, Mohamed Mhiri, Emilienne Greenfield, James P. via Pocket
analysis  ml  neural  text 
april 2019 by kintopp
Fundamentals of Data Visualization
This is an online preview of the book “Fundamentals of Data Visualization” to be published with O’Reilly Media, Inc. The book is meant as a guide to making visualizations that accurately reflect the data, tell a story, and look professional. via Pocket
analysis  books  data  visualization 
march 2019 by kintopp
Stereoscope – Hermeneutic Visualization in Literary Studies
Stereoscope is a web-based prototype for visualizing two core processes of literary studies - hermeneutic exploration of textual meaning and construction of arguments about texts. via Pocket
analysis  interactive  literature  text  visualization 
march 2019 by kintopp
Seminar »Methoden computergestützter Textanalyse«, Universität Luzern, HS 2015
Methoden computergestützter Textanalyse Universität Luzern Dozent/in Frederik Elwert, M.A. via Pocket
analysis  germany  syllabus  text  teach  python 
march 2019 by kintopp
Introduction: Re-viewing Digital Technologies and Art History /
A widespread opinion within the academic community is that art historians have been left behind by the digital turn in the humanities (see Greenhalgh 2004, Zorich 2012, and the in this issue). via Pocket
analysis  arthistory  images  paper  tools 
february 2019 by kintopp
Visual object recognition in datasets of pre-modern images | Heidelberg Collaboratory for Image Processing (HCI)
Objectives The main objectives of this research project are 1) to develop a tool for category-level object recognition of object categories such as crowns and swords in an image collection of medieval manuscripts 2) to identify different artistic workshops in the image collection 3) to develop a cla via Pocket
analysis  art  paper  visualization 
february 2019 by kintopp
Natural language and data prep at scale arrive with Tableau 2019.1 | Tableau Software
Tableau revolutionized analytics with a drag-and-drop interface, keeping you in the flow as you explore your data. With Ask Data, it’s even easier. Just type in a question and get your answer in the form of an interactive visualization. via Pocket
analysis  language  tools  visualization 
february 2019 by kintopp
Looking up stuff in an Early Modern corpus | Scalable Reading
The following is a discussion of a set of “search and sort” operations that could be useful in exploring the EEBO-TCP corpus of English books before 1700. via Pocket
analysis  history  indexing  regex  search  text  usa 
february 2019 by kintopp
Historiography’s Two Voices: Data Infrastructure and History at Scale in the Oxford Dictionary of National Biography (ODNB) « CA: Journal of Cultural Analytics
Peer-Reviewed By: Matt Erlin  Clusters: Data, Infrastructure Article DOI: 10.22148/16.028 Dataverse DOI: 10.7910/DVN/D3KFLP PDF DOI: 10.31235/osf.io/rbkdh Journal ISSN: 2371-4549 Cite: Christopher N. via Pocket
analysis  biography  oxford  paper  people 
february 2019 by kintopp
gepris.dfg.de
iArt: Ein interaktives Analyse- und Retrieval-Tool zur Unterstützung von bildorientierten Forschungsprozessen
analysis  art  arthistory  germany  images  munich  ml  deep 
february 2019 by kintopp
Text Mining with R
This is the website for Text Mining with R! Visit the GitHub repository for this site, find the book at O’Reilly, or buy it on Amazon. This work by Julia Silge and David Robinson is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 United States License. via Pocket
analysis  books  mining  text 
december 2018 by kintopp
Algorithms for Historical Maps
In our research, we invented a tool that assigns place markers to labels on old maps. What is that good for? Well, as you can see above, historical maps often contain a surprising amount of labeled places. This is interesting content one can extract from the map. via Pocket
algorithm  analysis  history  maps  metadata 
december 2018 by kintopp
DARIAH-DE :: Topics Explorer
Topics Explorer aims for simplicity and usability. If you are working with a large corpus (let’s say more than 200 documents, 5000 words each document), you may wish to use more sophisticated topic models such as those implemented in MALLET, which is known to be more robust than standard LDA. via Pocket
dariah  text  tools  topics  visualization  geo  analysis 
december 2018 by kintopp
Annif - tool for automated subject indexing and classification
Annif is a statistical automated indexing tool for libraries, archives and museums. After feeding it a SKOS vocabulary and existing openly available metadata from the Finna search engine for library, archive and museum collections, it knows how to assign subjects for new documents. via Pocket
analysis  classification  finland  indexing  ml  nlp  text  tools  vocabularies 
november 2018 by kintopp
Reading Machines — Technology and the Book
An experiential graduate seminar in the English Department at Northeastern University, Spring 2019. “Reading Machines” will pivot around the double valence of its title, outlining a literary history of new media from the hand-press period to the present. Our approach will draw on scholarship in book history, bibliography, media studies, and digital humanities.
analysis  books  dh  literature  syllabus  text  bibliography 
november 2018 by kintopp
DATeCH International Conference 2019 - Call for Papers - IMPACT Centre of Competence
The International DATeCH (Digital Access to Textual Cultural Heritage) conference brings together researchers and practitioners seeking innovative approaches for the creation, transformation and exploitation of historical documents in digital form. via Pocket
analysis  belgium  cfp  culture  handwriting  nlp  ocr  recognition  text 
november 2018 by kintopp
Course materials for 'Critical Perspectives in Cultural Data Analysis' at UT Austin
#Programming for Cultural Data Analysis syllabus and course materials via Pocket
analysis  culture  data  methodology  syllabus  teach 
november 2018 by kintopp
SemArt
Automatic art analysis has been mostly focused on classifying artworks into different artistic styles. However, understanding an artistic representation involves more complex processes, such as identifying the elements in the scene or recognizing author influences. via Pocket
analysis  art  paper  semantic  deep 
november 2018 by kintopp
ARIES
Art historians have traditionally used physical light boxes to prepare exhibits or curate collections. On a light box, they can place slides or printed images, move the images around at will, group them as desired, and visually compare them. via Pocket
analysis  arthistory  editing  metadata  tools  visualization 
november 2018 by kintopp
Shakespearean Sonnets' rhymes analysis - Online Technical Discussion Groups—Wolfram Community
Shakespearean sonnets are composed with the rhyme scheme ABAB CDCD EFEF GG , which means that each verse with the same label needs to rhyme. An example is the famous sonnet 18: A: Shall I compare thee to a summer’s day? B: Thou art more lovely and more temperate. via Pocket
analysis  poetry  shakespeare  text  wolfram 
november 2018 by kintopp
Katherine McDonough | Historian
I am a historian of France working primarily on the eighteenth century. I write periodically here about my projects, digital humanities, higher ed, archives, and radio/podcasts. via Pocket
analysis  france  geo  nlp  recognition  space  text  infrastructure 
november 2018 by kintopp
Beyond spreadsheets: Imagining the data journalism workflow of the future
The spreadsheet was a great innovation —in 1979 — but there’s so much that spreadsheets don’t do. Today we’re happy to announce Workbench, our next generation data journalism platform. Try out these demos to see how it works. via Pocket
analysis  excel  metadata  tools 
november 2018 by kintopp
Topic Model Tutorial
The Usage is simple: You create a corpus.txt file in which each line corresponds to a document. Then you execute the promoss.jar with Store the document metadata separated by semicolons in a file named meta.txt. The documents have to be put in a file named corpus. via Pocket
howto  learn  text  topics  analysis 
october 2018 by kintopp
GitHub - openeventdata/mordecai: Full text geoparsing as a Python library
Full text geoparsing as a Python library. Extract the place names from a piece of text, resolve them to the correct place, and return their coordinates and structured geographic information. Mordecai requires a running Elasticsearch service with Geonames in it. via Pocket
analysis  geo  metadata  python  tools 
october 2018 by kintopp
Revisiting the Disputed Federalist Papers: Historical Forensics with the Chaos Game Representation and AI—Wolfram Blog
Between October 1787 and April 1788, a series of essays was published under the pseudonym of “Publius.” Altogether, 77 appeared in four New York City periodicals, and a collection containing these and eight more appeared in book form as The Federalist soon after. via Pocket
analysis  text  wolfram 
october 2018 by kintopp
PUBLIC LECTURE: INGRID DAUBECHIES (​FRANCE) - YouTube
Mathematics can help Art Historians and Art Conservators in studying and understanding art works, their manufacture process and their state of conservation. The presentation will review several instances of such collaborations in the last decade or so. Some of them led (and are still leading) to int via Pocket
analysis  art  images  mathematics  talk 
august 2018 by kintopp
Ingrid Daubechies' Publication List
All "papers" (including various book chapters, a book, and a video) are listed in the chronological order of their creation. Boldface titles indicate original research results in refereed research journals or books. The other titles contain these same results in a different form (Ph.D. via Pocket
analysis  art  bibliography  mathematics  images 
august 2018 by kintopp
💡 Call for Proposals 💡 • Collections as Data - Part to Whole
A growing number of cultural heritage organizations have invested in the creation of collections that are amenable to computational use. Increasingly, the concept of collections as data is used to align efforts of this kind. via Pocket
analysis  cfp  culture  datasets  grants  libraries  mellon  museums  usa 
august 2018 by kintopp
Welcome to the Archives Unleashed Project
Jefferson Bailey is Director of Web Archiving at Internet Archive. Jefferson joined Internet Archive in Summer 2014 and manages Internet Archive’s web archiving services, including Archive-It, used by over 450 institutions to preserve the web. via Pocket
analysis  archives  data  nlp  tools  web  search 
july 2018 by kintopp
PERDIDO Project
This website provides a demonstration tool for the automatic reconstruction of itineraries extracted from narrative texts. The main functions are : Extraction of geographical information with natural language processing; Toponyms resolution in the context of an itinerary; Itinerary reconstruction
france  nlp  tools  itineraries  places  space  analysis  spain  italy  text 
july 2018 by kintopp
TextRazor - The Natural Language Processing API
TextRazor offers a complete cloud or self-hosted text analysis infrastructure. We combine state-of-the-art natural language processing techniques with a comprehensive knowledgebase of real-life facts to help rapidly extract the value from your documents, tweets or web pages. via Pocket
analysis  api  language  nlp  text  twitter 
july 2018 by kintopp
VISART IV
Where Computer Vision Meets Art
4th Workshop on Computer Vision for Art Analysis
9th September 2018, Munich, Germany
analysis  art  arthistory  cfp  conference  deep  germany  images  recognition  ml 
july 2018 by kintopp
Visual Dialog
Visual Dialog is a novel task that requires an AI agent to hold a meaningful dialog with humans in natural, conversational language about visual content. Specifically, given an image, a dialog history, and a follow-up question about the image, the agent has to answer the question. via Pocket
analysis  dialog  images  language  ml 
july 2018 by kintopp
FRED - Home
FRED is a machine reader for the Semantic Web: it is able to parse natural language text in 48 different languages and transform it to linked data. It is implemented in Python and available as REST service and as a Python library suite.
analysis  nlp  rdf  semantic  tools  language  api  text 
june 2018 by kintopp
Home | ColourLex
The first part of ColourLex consists of information on paintings with emphasis on pigment analysis.
The second key part of ColourLex are pages about the individual pigments.
The last part is a collection of resources on paintings, painters, pigments and the scientific methods used in the investigation of paintings.
analysis  art  colour  forensic  methodology 
june 2018 by kintopp
Mechanical Kubler: Visual Paths Through Time - Matthew Lincoln, PhD
Mechanical Kubler: Visual Paths Through Time I finally got the chance to push through a little idea about walking through visual time with a new Twitter bot I’m calling @MechaKubler. A pathway generated by Mechanical Kubler. via Pocket
art  images  recognition  analysis 
june 2018 by kintopp
One-shot object detection
This is more advanced than classification, which only tells you what the “main subject” of the image is — whereas object detection can find multiple objects, classify them, and locate where they are in the image. via Pocket
analysis  images  learn  recognition  classification  ml  deep 
june 2018 by kintopp
Sapping Attention: Meaning chains with word embeddings
Matthew Lincoln recently put up a Twitter bot that walks through chains of historical artwork by vector space similarity. https://twitter.com/matthewdlincoln/status/1003690836150792192. The idea comes from a Google project looking at paths that traverse similar paintings. via Pocket
analysis  demos  graphs  images  visualization  text 
june 2018 by kintopp
Call for Papers – DHQ Special Issue on “Digital Humanities & Film Studies: Analyzing the Modalities of Moving Images” | DHd-Blog
Die DHd AG Film und Video und Organisatoren des Anfang Mai stattgefunden Workshops “Computer-based Approaches for the Analysis of Film Style” möchten Sie gerne auf den unten in der Folge zum Workshop entstandenen öffentlichen Call for Papers aufmerksam machen: Call for Papers – DHQ Special I via Pocket
analysis  cfp  dh  film  journals 
june 2018 by kintopp
Wekinator | Software for real-time, interactive machine learning
The Wekinator is free, open source software originally created in 2009 by Rebecca Fiebrink. It allows anyone to use machine learning to build new musical instruments, gestural game controllers, computer vision or computer listening systems, and more. via Pocket
analysis  art  games  images  interactive  tools  ml 
june 2018 by kintopp
kepler.gl
Kepler.gl is a powerful open source geospatial analysis tool for large-scale data sets.
analysis  gis  maps  tools  visualization 
may 2018 by kintopp
philosophi.ca : CSDH-SCHN 2018 And CGSA 2018
These are my notes to CSDH-SCHN 2018 and then CGSA 2018. They are strictly my interpretation of the talks I went to. I also don't take notes all the time. via Pocket
analysis  conference  literature  report  text 
may 2018 by kintopp
Distant Reading for European Literary History – COST Action CA16204
This Action’s challenge is to create a vibrant and diverse network of researchers jointly developing the resources and methods necessary to change the way European literary history is written. Grounded in the Distant Reading paradigm (i.e. via Pocket
analysis  datasets  europe  infrastructure  language  literature  methodology  text 
may 2018 by kintopp
Text und Data Mining – in Recht, Wissenschaft und Gesellschaft
Die Tagung möchte das Problemfeld Text und Data Mining in Recht,
Wissenschaft und Gesellschaft aus vielfältiger, interdisziplinärer
Perspektive beleuchten und einen Dialog entstehen lassen, in dem die
Beteiligten ihre Anforderungen formulieren können, um so auf eine
produktive weitere Ausgestaltung der rechtlichen Rahmenbedingungen
des Text und Data Minings hinwirken zu können.
analysis  conference  germany  ip  legal  mining  text 
may 2018 by kintopp
The Code4Lib Journal – Implementing a Collaborative Workflow for Metadata Analysis, Quality Improvement, and Mapping
The University of North Texas (UNT) and the Oklahoma Historical Society (OHS) are collaborating to digitize, process, and make publicly available more than one million photographs from the Oklahoma Publishing Company’s historic photo archive. via Pocket
analysis  dev  diglib  metadata  quality 
may 2018 by kintopp
The Code4Lib Journal – Metadata Analysis at the Command-Line
Over the past few years the University of North Texas Libraries’ Digital Projects Unit (DPU) has developed a set of metadata analysis tools, processes, and methodologies aimed at helping to focus limited quality control resources on the areas of the collection where they might have the most bene via Pocket
analysis  diglib  metadata  quality  tools 
may 2018 by kintopp
GitHub - COMHIS/estc: ESTC analytics
This is an algorithmic toolkit for R, designed for transparent quantitative analysis of the British Library English Short Title Catalogue (ESTC) data collection. The package is under active, open development; the tools, analysis, and documentation are preliminary and constantly updated. via Pocket
analysis  bibliography  books  datasets  dev  lists  metadata  statistics  uk 
may 2018 by kintopp
LERA - Locate, Explore, Retrace and Apprehend complex text variants
The Histoire philosophique et politique des établissements et du commerce des Européens dans les deux Indes by Abbé Raynal (1713-1796) is one of the most influential, successful and scandalous books of 18th century Europe. via Pocket
analysis  text  tools  visualization 
may 2018 by kintopp
LODatio+
Query size estimation LODatio+ gives you an estimated number of how many data sources provide you with how many resources satisfying your information need. Ranking The results are ranked by the number of matching resources they contain. via Pocket
analysis  data  linkeddata  resources 
may 2018 by kintopp
Heidelberg University Publishing - heiUP
Visualisierungen spielen in den Wissenschaften eine wichtige Rolle im Forschungsprozess. Sie dienen der Illustration von gewonnener Erkenntnis, aber auch als eigenständiges Mittel der Erkenntnisgewinnung. Auch in der Linguistik sind solche Visualisierungen bedeutend. via Pocket
analysis  books  data  language  text  visualization 
may 2018 by kintopp
Where Computer Vision Meets Art (Munich, 8-14 Sep 18) - ArtHist.net: Netzwerk für Kunstgeschichte / Archiv
Following the success of the previous editions of the Workshop on Computer VISion for ART Analysis held in 2012, 2014 and 2016, we present the VISART IV workshop, in conjunction with the 2018 European Conference on Computer Vision (ECCV 2018). via Pocket
analysis  art  arthistory  cfp  conference  germany  images  recognition 
may 2018 by kintopp
« earlier      
per page:    204080120160

Copy this bookmark:





to read