Shumpei Miyawaki's repositories
awesome-ner
This repository groups together for the task of "Named Entity Recognition (NER)"
AIO2_DPR_baseline
https://www.nlp.ecei.tohoku.ac.jp/projects/aio/
Awesome-Multimodal-Large-Language-Models
:sparkles::sparkles:Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.
Awesome-OpenQA
オープンドメイン質問応答
awesome-Vision-and-Language-Pre-training
Recent Advances in Vision and Language Pre-training (VLP)
cv2_modules
cv2 勉強用
datasets
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
DensePhrases
ACL'2021: Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval Learns Passage Retrieval, Too
funer
Funer is Rule based Named Entity Recognition tool.
gitignore
A collection of useful .gitignore templates
GRiT
GRiT: A Generative Region-to-text Transformer for Object Understanding (https://arxiv.org/abs/2212.00280)
layout-model-training
The scripts for training Detectron2-based Layout Models on popular layout analysis datasets
Markdown-Tag
Add Markdown to any HTML using a <md> tag
pdfplumber
Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.
Pengenuity
Pengunuity is an experimental open-source autonomous AI Agent that aims to replicate the structure of human memory.
small-text
Active Learning for Text Classification in Python
streamlit
Streamlit — A faster way to build and share data apps.
streamlit-option-menu
streamlit-option-menu is a simple Streamlit component that allows users to select a single item from a list of options in a menu.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Transformers-Tutorials
This repository contains demos I made with the Transformers library by HuggingFace.
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
visprog
Official code for VisProg (CVPR 2023)
XFUND
XFUND: A Multilingual Form Understanding Benchmark