A Method for Coherent Storyline Extraction via Maximum Capacity Path Optimization

Large Concept Models: Language modeling in a sentence representation space

Efficient LLM inference on Slurm clusters using vLLM.

Code for collecting, processing, and preparing datasets for the Common Pile

Learning structural topic modeling using the stm R package.

TVB-UKBB Pipeline: TheVirtualBrain implementation of the UK Biobank pipeline

Data curation scripts of a comprehensive clinical, MRI, and MEG collection characterizing healthy research volunteers collected at the National Institute of Mental Health (NIMH) Intramural Research…

Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.

BERT score for text generation

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

TensorFlow code and pre-trained models for BERT

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

analyze text with empath

Functions for reading and pre-processing eye tracking data.

Data Analysis with Bootstrap Estimation in R

Data Analysis with Bootstrapped ESTimation

An R CRAN package for fixation and saccade detection in eye movement recordings.

An R package for analyzing scanpath patterns in eye movements

Detection of fixations and saccades in eyetracking data

Nostril: Nonsense String Evaluator

A corpus of 100,000 happy moments

The COVID-19 Real World Worry Datasets

TweetNLP for all the NLP enthusiasts working on Twitter! The Python library tweetnlp provides a collection of useful tools to analyze/understand tweets such as sentiment analysis, emoji prediction,…

An open-source archive that gathers, saves, shares and analyzes news homepages

Summarize existing representative LLMs text datasets.