Machine Translation Weekly 99: Vícejazyčné jazykové modely občas také můžou mít problémy
Vícejazyčné jazykové modely a technologie, které na jejich základě vznikají pomáhají zásadní mírou zpřístupňovat nástroje, které až donedávna byly dostupné pouze mluvčím velkých jazyků v bohatší části planety. Umožňují (do jisté míry) jednotně reprezentovat text v různých jazycích. Modely strojového učení trénované v jednom jazyce potom fungují i v ostatních jazycích, pro které nemáme buď žádná trénovací data nebo jen velmi málo dat. Předtrénované vícejazyčné jazykové modely také výrazně zvyšují kvalitu strojového překladu mezi jazyky, kde není k dispozici dostatek […]
Read more
The NLP Cypher | 01.23.22
The UnifiedSKG framework, which unifies 21 SKG tasks into the text-to-text format, aiming to promote systematic SKG research – instead of being exclusive to a single task, domain, or dataset. It shows that large language models like T5, with simple modification when necessary, achieve state-of-the-art performance on nearly all 21 tasks.
Read more
Modulo String Formatting in Python
If you’re writing modern Python code with Python 3, you’ll probably want to format your strings with Python f-strings. However, if you’re working with older Python codebases, you’re likely to encounter the string modulo operator for string formatting. If you’re reading or writing Python 2 code, it’ll help if you’re familiar with this technique. Because the syntax still works in Python 3, you might even see developers use it in modern Python codebases. In this tutorial, you’ll learn how to: […]
Read more
A python package for binomial confidence intervals
Pynomial (pronounced like “binomial”) is a lightweight python library for implementing the many confidence intervals for the risk parameter of a binomial model. Pynomial is more or less a python port of the R library {binom} by Sundar Dorai-Raj. As a point of philosophy and until otherwise stated, if {binom} does a thing then so should pynomial (e.g. error throwing or handling cases when the number of successes is the same as the number of trials). The following confidence intervals […]
Read more
Aula – a school system widely used in Denmark, as you can see and read about in the python file
Hello, thank you for reading this first of all.This is a Aula-API Wrapper for.. – Aula! Aula is a school system widely used in Denmark, as you can see and read about in the python file, they’re shitters…This was an active project until recently, when we abandoned it. Therefore this is a ‘Discontinued API – Wrapper’.If we were to directly clown them, we would include the overall law, they’re breaking.. – So here is it 🙂 –The company behind Aula, […]
Read more
A Discord bot to track you and your friends’ Wordle scores
A Discord bot to track you and your friends’ Wordle scores, so you can see who’s the best! To submit a score to wordle-bot, just paste the Wordle score share in a Discord server that wordle-bot is a member of, as shown in the demo photo below. Note that your scores are bound to your Discord user id, not any particular server, so you can submit a score on one server and have it shown in another server’s rankings. To […]
Read more
K-means real-time segmentation
The project’s goal is to show a real world application of image segmentation using k means algorithm. features of the code: segmentation of an image (can use the webcam class or upload your own) define which clusters you would like to hide (in black color) –> easy way to reduce noise in an image and make easier detections example of the results on my data: (different combinations of cluster coloring) webcam class output: (yea thats me) GitHub To finish […]
Read more