asahi417

Asahi Ushio's repositories

tner

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"

Language:PythonMIT349 10 43

lm-question-generation

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

Language:PythonMIT257 3 20

lmppl

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).

Language:PythonMIT87 4 9

kex

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

Language:PythonMIT53 3 5

relbert

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.

Language:PythonMIT45 5 7

wikiart-image-dataset

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`.

Language:Python41 1 4

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 dropout.

Language:PythonMIT30 2 3

DeepDomainAdaptation

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 distribution optimal transportation)

Language:PythonMIT26 20

analogy-language-model

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

Language:Python22 40

lm-vocab-trimmer

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 python-library vocabtrimmer, that remove irrelevant tokens from a multilingual LM vocabulary for the target language.

Language:PythonMIT20 2 3

ConditionalVariationalAutoEncoder

Implement Conditional VAE and train on MNIST by tensorflow 1.3.0.

Language:PythonMIT9 10

DocumentClassification

Implementation CNN and LSTM with character-level feature for document classification model by tensorflow 1.3.0.

Language:PythonMIT9 10

AnalogyTools

This repository is aimed to collect resources for word analogy and lexical relation research.

Language:PythonNOASSERTION5 1 1

CycleGAN

Tensorflow cycle GAN implementation with TFRecord data format and Tensorboard visualization. Show couple of generated examples from horse2zebra and monet2photo.

Language:PythonMIT3 10

visual-wsd-baseline

Language:Python3 40

WassersteinGAN

Tensorflow Wasserstein GAN implementation with TFRecord data format. WGAN, WGAN-GP (gradient penalty), DCGAN and showing example usage with CelebA dataset.

Language:PythonMIT2 10