systats/textlearnR
A simple collection of well working NLP models (Keras, H2O, StarSpace) tuned and benchmarked on a variety of datasets.
Building accurate classification models from text data can be complicated and time-consuming due to the many parameters involved. This tool simplifies the process by providing a collection of pre-tuned and benchmarked text classification models that can be easily trained. It takes raw text and category labels as input and outputs a trained model capable of classifying new text, designed for data scientists and analysts working with text-heavy datasets.
No commits in the last 6 months.
Use this if you need to quickly train and compare different machine learning models for text classification tasks without deep knowledge of hyperparameter tuning.
Not ideal if your primary goal is to perform tasks beyond text classification, such as text generation or entity extraction.
Stars
18
Forks
1
Language
R
License
—
Category
Last pushed
Mar 08, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/systats/textlearnR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
quanteda/quanteda
An R package for the Quantitative Analysis of Textual Data
juliasilge/tidytext
Text mining using tidy tools :sparkles::page_facing_up::sparkles:
massimoaria/tall
Text Analysis for aLL
keyATM/keyATM
An R package for Keyword Assisted Topic Models
gagolews/stringi
Fast and Portable Character String Processing in R (with the Unicode ICU)