Our notes from reading. Instruction Tuning for Large Language Models: A Survey.
Category: Resources
IPTC Media Topics
The IPTC (International Press Telecommunications Council) calls itself the global standards body for news media. In this article we focus on one of its standards: Media Topics. This standard contains a subject taxonomy for media, which is a topic hierarchy that can be used to classify news articles. *Example of a subset of Media Topics…
The importance of tags in online news media
This article presents an overview of what tags are in the context of news media, how they can benefit readers and publishers, and why using Geneea NLP for tagging might be a good idea.
Robotic journalism
What is robotic journalism? Will journalists be replaced by robots and AI 🤖? How does media automation work? To what extent is Czech more complicated for AI and NLP than, for example, English? Petr Hamerník and Jiří Hana, co-founders of Geneea, tell you about natural language processing in a broadcast Zátiší with Ales Vojir on Radio 1 –…
Analysis of Czech political posts
Our text analysis can even come in handy when assessing social media posts. Check out some of the results of our collaboration with Transparency International ČR. The article focuses on the use of paid and unpaid posts written by Czech politicians and political parties. Read more…
The importance of tags in online media
Our article about the importance of tags in online media was published by one of the world’s most-visited websites for journalists and publishers. Geneea’s linguistic data analyst Sofie Ferklová described various ways in which tags can benefit news publishers. Read more…
Geneea, Genneea, Geenea, Geeneea…
When launching a startup, you must take care of many things. Choosing the right name is one of them and it’s far from easy. Apart from an available domain, you need a name that is unique, short, and ideally easy to pronounce and remember. Its usability for foreign speakers is also something to consider. We…
Interested in business advice? Your customers will give you the best one
Understanding customer feedback via Artificial Intelligence and Natural Language Processing To stay successful and grow, businesses need to make wise decisions based on qualified and effective analyses of the right data. An increasing amount of data comes from the customers via social media and recommendation sites in the form of post-visit reviews, posts, and mentions….
How to find the best restaurant using sentiment analysis
IT students used our API in their projects. Learn about their experience of performing sentiment analysis to find the best restaurant in town. Read more…
How to speed up e-shops’ customer support
IT students used our API in their projects. See how they analyzed an e-shop’s emails to find the ones that are important and filtered out automatic messages and spam to make it easy for the e-shop to address customers’ concerns faster. Read more…
Analyzing customer feedback in e‑commerce
Covering new trends in e-commerce, FEEDIT.CZ introduced Geneea to its readers among several other emerging solutions offering AI-based advanced text analysis that are available to the quickly growing local e-commerce sector. Read more…
Would you trust AI to recommend you a place to eat?
IT students used our API in their projects. Find out how they discovered the best restaurants in Prague by analyzing real customer reviews, proving that data analysis can help people make good, conscious decisions. Read more…
Identifying trends in recipe ingredients using NLP
IT students used our API in their projects. See how they analyzed the recipes section of the most visited Czech website dedicated to mothers and their babies. Finding insights about the stock market involves pretty much the same process. Read more…
Finding a needle in a haystack of text
TLDR: Anomaly detection over text data is important. Geneea offers it as a service. In Keboola Connection, it is available as well; for now, in beta version upon request. Understanding a lot of text Our clients get a lot of written feedback from their customers – support tickets, emails, or Facebook posts. For some of…
William Shakespeare’s Plays in the Hands of Text Analytics
William Shakespeare, one of the greatest playwrights of all times, died 400 years ago, in 1616. At this occasion, we analyzed the content of three of his most popular plays solely via our text analytics software the Interpretor. Despite being written more than 400 years ago, Shakespeare’s comedies and dramas still speak to us. They…