Asahi Ushio

Language model fine-tuning on NER with an easy interface and cross-domain evaluation. "T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition, EACL 2021"

asahi417

The official implementation of "BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?, ACL 2021 main conference"

asahi417

Tensorflow deep learning based domain adaptation model implementations with experiment of estimate MNIST by SVHN data (SVHN -> MNIST): DANN (domain-adversarial neural network), Deep JDOT (joint distri...

asahi417

Kex is a python library for unsupervised keyword extraction from a document, providing an easy interface and benchmarks on 15 public datasets.

asahi417

Multilingual/multidomain question generation datasets, models, and python library for question generation.

asahi417

Implement modern LSTM cell by tensorflow and test them by language modeling task for PTB. Highway State Gating, Hypernets, Recurrent Highway, Attention, Layer norm, Recurrent dropout, Variational drop...

asahi417

The official implementation of "Distilling Relation Embeddings from Pre-trained Language Models, EMNLP 2021 main conference", a high-quality relation embedding based on language models.

asahi417

We release WikiART Crawler, a python-library to download/process images from WikiART via WikiART API, and two image datasets: `WikiART Face` and `WikiART General`.

asahi417

Vocabulary Trimming (VT) is a model compression technique, which reduces a multilingual LM vocabulary to a target language by deleting irrelevant tokens from its vocabulary. This repository contains a...

asahi417

Calculate perplexity on a text with pre-trained language models. Support MLM (eg. DeBERTa), recurrent LM (eg. GPT3), and encoder-decoder LM (eg. Flan-T5).

asahi417