nlproc

🚪✊Knock Knock: Get notified when your training ends with only two additional lines of code

OCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models (accepted at EACL2021 demo track)

Chain together LLMs for reasoning & orchestrate multiple large models for accomplishing complex tasks

Augmenty is an augmentation library based on spaCy for augmenting texts.

Easier Automatic Sentence Simplification Evaluation

EMNLP 2019: Generating Personalized Recipes from Historical User Preferences

Python library for feature selection for text features. It has filter method, genetic algorithm and TextFeatureSelectionEnsemble for improving text classification models. Helps improve your machine learning models

TURJUMAN, a neural toolkit for translating from 20 languages into Modern Standard Arabic (MSA).

A diff tool for language models

Named Entity Recognition with BiLSTM, CRF, and Attention-based models implemented in PyTorch for Indonesian News.

A Streamlit app to extract keywords using KeyBert

My thesis on "Open Source Code and Low Resource Languages" for an MSc in Language Science and Technology at Saarland University

Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"

How to build a multi-label sentiment classifiers with Tez and PyTorch

Text Anonymization app with Streamlit and Spacy

Code and data of the ACL 2021 paper "Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution"

Code base for the EMNLP 2021 paper, "Multi-granularity Textual Adversarial Attack with Behavior Cloning".

Code for "CharManteau: Character Embedding Models For Portmanteau Creation. EMNLP 2017. Varun Gangal*, Harsh Jhamtani*, Graham Neubig, Eduard Hovy, Eric Nyberg"

Leverage the power of the Google Natural Language API NLP to retrieve entity relationships from Wikipedia URLs or topics! Get interactive networkx graphs of connected entities!

Grupo de Aprendizaje de Procesamiento del Lenguaje Natural, lanzado por Lingwars