wangwisdom's repositories
bicleaner
Bicleaner is a parallel corpus classifier/cleaner that aims at detecting noisy sentence pairs in a parallel corpus.
CDial-GPT
A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models
dlcl
The implementation of "Learning Deep Transformer Models for Machine Translation"
fast_align
Simple, fast unsupervised word aligner
HanLP
自然语言处理 中文分词 词性标注 命名实体识别 依存句法分析 关键词提取 新词发现 短语提取 自动摘要 文本分类 拼音简繁
mecab
Yet another Japanese morphological analyzer
opencyc
A fork of opencyc which adds auto-complete to sentence assertion in the browser interface.
Rasa-UI
A simple Rasa UI
rasa-webchat
A feature-rich chat widget for Rasa and Botfront
sacrebleu
Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons
tensor2tensor-optuna
Hyperparameter tuning with Optuna integrated tensor2tensor.
transformer-aan
souce code for "Accelerating Neural Transformer via an Average Attention Network"