LettuceDetect is a hallucination detection framework for RAG applications.

AdaSeq: An All-in-One Library for Developing State-of-the-Art Sequence Understanding Models

A Simple but Powerful SOTA NER Model | Official Code For Label Supervised LLaMA Finetuning

Transformer-based models implemented in tensorflow 2.x(using keras).

Code and data form the paper BERT Got a Date: Introducing Transformers to Temporal Tagging

A collection of datasets for Ukrainian language

Lightweight self-hosted span annotation tool

Token classification using Phobert Models for Vietnamese

The MERIT Dataset is a fully synthetic, labeled dataset created for training and benchmarking LLMs on Visually Rich Document Understanding tasks. It is also designed to help detect biases and improve interpretability in LLMs, where we are actively working. This repository is actively maintained, and new features are continuously being added.

Applied Deep Learning 深度學習之應用 by Vivian Chen 陳縕儂 at NTU CSIE

Implementation of the paper, MAPLE - MAsking words to generate blackout Poetry using sequence-to-sequence LEarning, ICNLSP 2021

Data and code for the paper "ID10M: Idiom Identification in 10 Languages" (NAACL 2022).

Labeled Russian text token-by-token for training models for NER task based samples got from parsing different resources and generated by ChatGPT.

MAPLEv2 - Multi-task Approach for generating blackout Poetry with Linguistic Evaluation

Develop a deep learning model to accurately restore Vietnamese diacritics.

A library to help with common NLP pre-processing tasks.

Data pipelines for both TensorFlow and PyTorch!

Sequence-tagging using deep learning

Scrap, token classification and model deployment for a selective process.

API for Yoda-NER and Yoda-FITS model. NLP models for Google Feed product optimization