-
common_crawl_corpus Public
Scripts for building a geo-located web corpus using Common Crawl data
-
pacific_CodeSwitch Public
Code-switching detection for Pacific languages
-
c2xg Public
A Python package for learning, evaluating, annotating, and extracting vector representations of construction grammars
-
text_analytics Public
Basic text analytics and natural language processing in Python
-
earthLings Public
Corpus-based language and dialect mapping
-
geoLid Public
Geographically-informed language identification
-
corpus_similarity Public
Measure the similarity of text corpora for 74 languages
-
corpus_analysis Public
Code notebooks as exercises to accompany the text_analytics package
-
eng_mri Public
Predict whether individual words are ENG or MRI.
Python GNU General Public License v3.0 UpdatedJul 4, 2021 -
idNet Public
Neural net language identification for many languages on short texts plus construction-based dialectometry
-
-
political_classification Public
Code from "Profile-based authorship analysis"
{{ message }}