Introduction Machine Learning approaches in NLP have been shown to be able to solve a wide range of tasks after being trained from scratch on an appropriate training corpus. While this is impressive, it often does not correspond to the demand in many real-world scenarios. Often relevant prior knowledge exists – in the case of … Continue reading Jumpstart your Machine Learning efforts by importing structured knowledge
Do you know this situation: You have loads of documents to categorize, no training corpus......and you don't want to ask the experts to build a categorizer for you? Our quick tutorial explains how you can do it on your own: Train your own machine learning model without having to start programming.Download The machines should adapt … Continue reading Quick tutorial: Easy document categorization with Kairntech
In a few words Interested in what Kairntech does and what it could mean for you but no time to read lengthy papers or watch our video tutorials? Here's a treat for you: Kairntech cheatsheetDownload Get a quick impression of what Kairntech can contribute to your plans to make AI work on your document analysis projects.
Retrospective In May 2020 we had scheduled two webinars, demonstrating the ease of setting up a document analysis project to process complex call for tenders using the machine learning approaches in the Kairntech Sherpa. We had done that on two occasions, in english and french. Please find the respective recordings of the events here: https://www.youtube.com/watch?v=8PO4L4P2GZU … Continue reading Kairntech Webinar recordings from May 2020
A paper on the Kairntech Platform This spring has brought a lot of confusion into many calendars: Many workshops and conferences had to be cancelled, sometimes right at the moment when the paper that was planned to be submitted was ready. For instance I had been looking forward to a few nice days in Marseille … Continue reading Kairntech: An ML Platform and API for the Enrichment of (not only) Scientific Content
Processing "Call for Tender" Documents with the Kairntech platform Tuesday May 12, 2020, 16:00 CESTPresenters: Stefan Geißler and Vincent NibartDuration: 60min. Please register to receive the link for participation: registration is closed Many important business processes require finding, collecting and analysing information from text documents. Machine Learning can provide valuable support in making these processes easier, quicker and less … Continue reading Kairntech Webinar: Using Machine Learning to Automate Document Analysis Tasks
Find the planned Kairntech contribution here Due to the ongoing Covid19 pandemic, yet another conference had to be cancelled by the organizers: The Deutscher Bibliothekartag in Hannover (#bibtag20) where we had planned to present our approach to analyze and annotate text documents using our Kairntech platform. Our planned poster (in german): Kairntech Bibliothekartag 2020Download We are … Continue reading Deutscher Bibliothekartag 2020 in Hannover cancelled
Introduction The Kairntech platform goes a long way in order to give the users access to powerful machine learning capabilities wrapped inside an intuitive, easy-to-use GUI. While this is key for allowing non-technical users and domain experts without data science background to use the platform, there is a second approach to working with it: Using … Continue reading How to access the Kairntech API – Introducing a simple python client
NLP and Knowledge Base The broad success of quantitative methods such as deep learning in NLP sometimes risks to downplay the importance of explicit, symbolic knowledge required for many NLP task: Good named entity recognition (NER) for instance not only needs to recognize the entities (where learning based methods are important), but also normalize, disambiguate … Continue reading Named Entity Recognition with Wikidata: Always up to date!
So many ML libraries and algorithms... In the Machine Learning field there is a great wealth of well-studied approaches to various learning problems and users often experience the agony of choice when having to decide for one specific algorithm for a given problem. Algorithms may differ significantly in their runtime behavior, their memory and data … Continue reading Experimenting with ML algorithms… without having to study Python.