A curated list of resources for Learning with Noisy Labels

textlint rule preset for Japanese.

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

Japanese Realistic Textual Entailment Corpus (NLP 2020, LREC 2020)

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

This repository contains code and data download scripts for the paper "Intermediate Training of BERT for Product Matching" by Ralph Peeters, Christian Bizer and Goran Glavaš.

This repository contains source code for the TaBERT model, a pre-trained language model for learning joint representations of natural language utterances and (semi-)structured tables for semantic p…

Multi Task Vision and Language

A paper list for aspect based sentiment analysis.

Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"

Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".

A Python framework for sequence labeling evaluation(named-entity recognition, pos tagging, etc...)

Tutorial to train fastText with Japanese corpus

A technical report on convolution arithmetic in the context of deep learning

⛔️ DEPRECATED – See https://github.com/ageron/handson-ml3 instead.

4th Place Solution for Mercari Price Suggestion Competition on Kaggle using DeepFM variant.

『ゼロから作る Deep Learning』(O'Reilly Japan, 2016)

An attempt of training DNN models to predict ad click-through rate, implemented with Theano.

A simple deep learning library for estimating a set of tags and extracting semantic feature vectors from given illustrations.

Neologism dictionary based on the language resources on the Web for mecab-ipadic

Scalable Topic Modeling using Variational Inference in MapReduce