Pinned Repositories
arts401-2022
binder-gensim-mallet
This repository is designed for students in DIGI405 at the University of Canterbury to do topic modeling through their browser using Binder. It is relevant for others who want to do topic modeling through a browser with their own corpus.
cite-this
Academic research isn't just published in journals. If you are blogging, releasing software, data-sets and other kinds of digital outputs via a Github pages site (or using Jekyll via another host) here's a way to make this work easy to cite, with text-based recommended citations and auto-importing to citation managers (e.g. EndNote etc).
colab-gensim-mallet
This repository is designed for students in DIGI405 at the University of Canterbury to do topic modeling through their browser using Google Colab. It is relevant for others who want to do topic modeling through a browser with their own corpus.
corpress
Create a text corpus from a WordPress site using the WordPress API.
coverage
DIGI405-lab-exercise-3
docker-kaldi-asr
generate-a-corpus-with-an-LLM
The notebook in this repository is provided for students in DIGI405 at the University of Canterbury to query a Large Language Model (LLM) to generate a corpus. Students can adapt the code to generate their own data for an assignment.
polsci's Repositories
polsci/colab-gensim-mallet
This repository is designed for students in DIGI405 at the University of Canterbury to do topic modeling through their browser using Google Colab. It is relevant for others who want to do topic modeling through a browser with their own corpus.
polsci/binder-gensim-mallet
This repository is designed for students in DIGI405 at the University of Canterbury to do topic modeling through their browser using Binder. It is relevant for others who want to do topic modeling through a browser with their own corpus.
polsci/generate-a-corpus-with-an-LLM
The notebook in this repository is provided for students in DIGI405 at the University of Canterbury to query a Large Language Model (LLM) to generate a corpus. Students can adapt the code to generate their own data for an assignment.
polsci/corpress
Create a text corpus from a WordPress site using the WordPress API.
polsci/arts401-2022
polsci/cite-this
Academic research isn't just published in journals. If you are blogging, releasing software, data-sets and other kinds of digital outputs via a Github pages site (or using Jekyll via another host) here's a way to make this work easy to cite, with text-based recommended citations and auto-importing to citation managers (e.g. EndNote etc).
polsci/coverage
polsci/DIGI405-lab-exercise-3
polsci/docker-kaldi-asr
polsci/getpaperspast
A scraper to get material from Papers Past (that isn't accessible via DigitalNZ).
polsci/QSample-docker
Dockerfile to run QSample ("a natural language processing tool for automatically detecting quotations in text") https://github.com/christianscheible/qsample
polsci/scraping-garden-party
A small site based on the short story collection "The Garden Party: and Other Stories" by Katherine Mansfield. This site was built for a web scraping exercise for students at the University of Canterbury.
polsci/tiny-corenlp-docker
A minimal Docker image for running Stanford CoreNLP Server.
polsci/named-entities-with-llm-task
The notebook in this repository is provided for students in DIGI405 at the University of Canterbury for a lab task that involves writing a query to use a Large Language Model (LLM) to extract named entities from arbitrary texts.
polsci/twitter-emotion-recognition
Models for predicting emotions from English tweets.
polsci/wayback-as-research-tool
Python notebooks to download an archive of a website from Wayback Machine