Lists (4)
Sort Name ascending (A-Z)
Stars
Azure Data SQL Samples - Official Microsoft GitHub Repository containing code samples for SQL Server, Azure SQL, Azure Synapse, and Azure SQL Edge
Im Datensatz 'COVID-19-Todesfälle in Deutschland' werden die Todesfälle in Bezug auf COVID-19 in Deutschland bereitgestellt. Darüber hinaus wird neben der Anzahl der übermittelten Todesfälle der Fa…
Replication materials for "Exposure to the Russian Internet Research Agency foreign influence campaign on Twitter in the 2016 US Election and its relationship to attitudes and voting behavior"
Im Datensatz '7-Tage-Inzidenz von COVID-19 in Deutschland' werden die aktuellen 7-Tage-Inzidenzen der nach den Vorgaben des Infektionsschutzgesetzes - IfSG - an das RKI übermittelten COVID-19-Fälle…
Efficient few-shot learning with Sentence Transformers
Course repository for the session "Hands-on Transformers: Fine-Tune your own BERT and GPT" of the Data Science Summer School 2023
Create embed graph page from Notion Database.
Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"
[EMNLP 2021] Improving and Simplifying Pattern Exploiting Training
Functions that help to work with dictionaries that include search strings (and wildcards) consisting of multiple words
A package designed to measure populism in text with a German dictionary.
A simple web scraping tool to get articles from Dow Jones Factiva
Code for Paper: “Low-Resource” Text Classification: A Parameter-Free Classification Method with Compressors
Natural Language Processing with Flair, published by Packt
Ten Thousand German News Articles Dataset for Topic Classification
A Corpus for Multilingual Document Classification in Eight Languages.
A very simple framework for state-of-the-art Natural Language Processing (NLP)
A utility to check if a document's contents are plagiarised
Python package to interact with Factiva news-related APIs. Services are described in the Dow Jones Developer Platform.
article collector utils for WE1S (WhatEvery1Says)
📰 Working with newspaper data from 'LexisNexis'