All Projects → DongjunLee → Char Rnn Tensorflow

DongjunLee / Char Rnn Tensorflow

Multi-layer Recurrent Neural Networks for character-level language models implements by TensorFlow

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Char Rnn Tensorflow

Pytorch Bert Crf Ner
KoBERT와 CRF로 만든 한국어 개체명인식기 (BERT+CRF based Named Entity Recognition model for Korean)
Stars: ✭ 236 (+306.9%)
Mutual labels:  korean, natural-language-processing
Oie Resources
A curated list of Open Information Extraction (OIE) resources: papers, code, data, etc.
Stars: ✭ 283 (+387.93%)
Mutual labels:  dataset, natural-language-processing
Open-korean-corpora
Open Korean NLP Dataset Curation for the Users All Around the Globe
Stars: ✭ 82 (+41.38%)
Mutual labels:  dataset, korean
Chazutsu
The tool to make NLP datasets ready to use
Stars: ✭ 238 (+310.34%)
Mutual labels:  dataset, natural-language-processing
Hate Speech And Offensive Language
Repository for the paper "Automated Hate Speech Detection and the Problem of Offensive Language", ICWSM 2017
Stars: ✭ 543 (+836.21%)
Mutual labels:  dataset, natural-language-processing
Kor2vec
Library for Korean morpheme and word vector representation
Stars: ✭ 64 (+10.34%)
Mutual labels:  korean, natural-language-processing
Coarij
Corpus of Annual Reports in Japan
Stars: ✭ 55 (-5.17%)
Mutual labels:  dataset, natural-language-processing
Prosody
Helsinki Prosody Corpus and A System for Predicting Prosodic Prominence from Text
Stars: ✭ 139 (+139.66%)
Mutual labels:  dataset, natural-language-processing
Doccano
Open source annotation tool for machine learning practitioners.
Stars: ✭ 5,600 (+9555.17%)
Mutual labels:  dataset, natural-language-processing
Open Korean Text
Open Korean Text Processor - An Open-source Korean Text Processor
Stars: ✭ 438 (+655.17%)
Mutual labels:  korean, natural-language-processing
Korean Hate Speech
Korean HateSpeech Dataset
Stars: ✭ 192 (+231.03%)
Mutual labels:  dataset, natural-language-processing
Wikisql
A large annotated semantic parsing corpus for developing natural language interfaces.
Stars: ✭ 965 (+1563.79%)
Mutual labels:  dataset, natural-language-processing
Nlp bahasa resources
A Curated List of Dataset and Usable Library Resources for NLP in Bahasa Indonesia
Stars: ✭ 158 (+172.41%)
Mutual labels:  dataset, natural-language-processing
Hunspell Dict Ko
Korean spellchecking dictionary for Hunspell
Stars: ✭ 187 (+222.41%)
Mutual labels:  korean, natural-language-processing
Pytorch Nlp
Basic Utilities for PyTorch Natural Language Processing (NLP)
Stars: ✭ 1,996 (+3341.38%)
Mutual labels:  dataset, natural-language-processing
Fakenewscorpus
A dataset of millions of news articles scraped from a curated list of data sources.
Stars: ✭ 255 (+339.66%)
Mutual labels:  dataset, natural-language-processing
Awesome Hungarian Nlp
A curated list of NLP resources for Hungarian
Stars: ✭ 121 (+108.62%)
Mutual labels:  dataset, natural-language-processing
Mams For Absa
A Multi-Aspect Multi-Sentiment Dataset for aspect-based sentiment analysis.
Stars: ✭ 135 (+132.76%)
Mutual labels:  dataset, natural-language-processing
Text2sql Data
A collection of datasets that pair questions with SQL queries.
Stars: ✭ 287 (+394.83%)
Mutual labels:  dataset, natural-language-processing
Insuranceqa Corpus Zh
🚁 保险行业语料库,聊天机器人
Stars: ✭ 821 (+1315.52%)
Mutual labels:  dataset, natural-language-processing

char-rnn hb-research

This code implements multi-layer Recurrent Neural Network (RNN, LSTM, and GRU) for training/sampling from character-level language models.

Requirements

  • Python 3.6
  • TensorFlow 1.4
  • hb-config

Features

Config

example: check_tiny.yml

data:
  data_dir: 'data/tiny_lyricskor'
model:
  batch_size: 4
  input_keep_prob: 0.8
  log_dir: 'logs'
  num_layers: 1
  output_keep_prob: 0.8
  rnn_size: 64
  seq_length: 20
train:
  train_steps: 10000
  model_dir: 'tiny_checkpoints'
  save_every: 1
  learning_rate: 0.001
  loss_hook_n_iter: 100
  check_hook_n_iter: 1000
  min_eval_frequency: 100

Usage

First, check if the model is valid.

python main.py --config check_tiny --mode train

Then, train the model

python main.py --config kor_ballad --mode train_and_evaluate

After training, generate Korean Samhangsi.

python generator.py --config kor_ballad --word 삼행시

Samhangsi Examples

  • 삼행시
삼이야 그리움이 좇아 사랑은늘 도망가
행른 잊어버리고 그대 이 세상
시제 너의 곁을 떠나면 빗물에 꽃씨하나 흘러가듯
  • 기계
기를 바라보네 두 손 잡고 고개 끄덕여 달라 하기에
계 울고 싶어 내 맘을 떠나가던 날
  • 여름
여도 지금하럼 커피는 날개니
름다웠던 그대모습 다시 볼 수 없는것 알아요
  • 커피
커나가 그래 돌아서 눈 감으면 잊을까
피고 내가 가고 싶지 아파 만날 날 기다려왔어

Example with kino-bot

images

images

Reference

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].