Asahi Ushio (@asahi417)
github

asahi417

Twitter logo Share LinkedIn logo Share Facebook logo Share
  • Stars
    star
    1,086
  • Global Rank 28,263 (Top 1.0 %)
  • Followers 83
  • Following 9
  • Registered almost 9 years ago
  • Most used languages
    Python
         100.0 %
  • Location πŸ‡―πŸ‡΅ Japan
  • Country Total Rank 1,674
  • Country Ranking
    Python
         69

Top repositories

1

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"
Python
376
star
2

lm-question-generation

Multilingual/multidomain question generation datasets, models, and python library for question generation.
Python
302
star
3

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).
Python
119
star
4

kex

Kex is a python library for unsupervised keyword extraction from a document, providing an easy interface and benchmarks on 15 public datasets.
Python
53
star
5

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`.
Python
47
star
6

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.
Python
46
star
7

LSTMCell

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.
Python
30
star
8

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.
Python
29
star
9

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)
Python
26
star
10

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"
Python
23
star
11

ConditionalVariationalAutoEncoder

Implement Conditional VAE and train on MNIST by tensorflow 1.3.0.
Python
10
star
12

DocumentClassification

Implementation CNN and LSTM with character-level feature for document classification model by tensorflow 1.3.0.
Python
9
star
13

AnalogyTools

This repository is aimed to collect resources for word analogy and lexical relation research.
Python
4
star
14

CycleGAN

Tensorflow cycle GAN implementation with TFRecord data format and Tensorboard visualization. Show couple of generated examples from horse2zebra and monet2photo.
Python
3
star
15

visual-wsd-baseline

Python
3
star
16

zeroshot-metaphor

Python
2
star
17

WassersteinGAN

Tensorflow Wasserstein GAN implementation with TFRecord data format. WGAN, WGAN-GP (gradient penalty), DCGAN and showing example usage with CelebA dataset.
Python
2
star
18

BitcoinPriceAccumulator

Micro service to get bitcoin price from bitflyer API and accumulate to postgres SQL.
Python
1
star
19

firstcut

Audio/video editor: detecting silent interval and eliminated them from the original audio/video.
Python
1
star
20

StochasticOptimizers

Simple stochastic optimizer comparison over classification tasks.
Python
1
star
21

one-shot-analogical-reasoning

1
star
22

SemanticSegmentation

Tensorflow implementation of DeepLab v3+. Show results trained over PASCAL data.
Python
1
star
23

distil-whisper-ja

Python
1
star
24

pytorch-language-model

Pytorch language modeling.
Python
1
star