AINLP's repositories
MeCab-Chinese
Chinese morphological analysis with Word Segment and POS Tagging data for MeCab
allennlp
A natural language processing toolkit using state-of-the-art deep learning models.
AutoPhrase
AutoPhrase: Automated Phrase Mining from Massive Text Corpora
bible-corpus
A multilingual parallel corpus created from translations of the Bible.
brook
Brook is a cross-platform(Linux/MacOS/Windows/Android/iOS) proxy software
brpc
Most common RPC framework used throughout Baidu, with 600,000+ instances and 500+ kinds of services, called "baidu-rpc" inside Baidu.
chaizi
漢語拆字字典
deep-siamese-text-similarity
Tensorflow based implementation of deep siamese LSTM network to capture phrase/sentence similarity using character embeddings
deepnlp
Deep Learning NLP Pipeline implemented on Tensorflow
discourse
A platform for community discussion. Free, open, simple.
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit
fairseq-py
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
fastText_multilingual
Multilingual word vectors in 78 languages
got-book-6
RNN trained on the first five GOT books
incubator-airflow
Apache Airflow (Incubating)
interactive-coding-challenges
Huge update! Interactive Python coding interview challenges (algorithms and data structures). Includes Anki flashcards.
NanGeMT
NanGe - A Rule-based Chinese-English Machine Translation System
ngx_http_google_filter_module
Nginx Module for Google Mirror
ParlAI
A framework for training and evaluating AI models on a variety of openly available dialog datasets.
pipesocks
A pipe-like SOCKS5 tunnel system.
sent2vec
General purpose unsupervised sentence representations
sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
SIF
sentence embedding by Smooth Inverse Frequency weighting scheme
skip-thoughts
Sent2Vec encoder and training code from the paper "Skip-Thought Vectors"
Synonyms
这是一个可以标准化用户搜索关键词,并且返回近义的候选搜索关键词的程序。
Text-Summarization-with-Amazon-Reviews
A seq2seq model that can generate summaries from fine food reviews on Amazon.
weibo_terminater
Final Weibo Crawler Scrap Anything From Weibo, comments, weibo contents, followers, anythings. The Terminator
word2vec_pipeline
Pipeline to turn input text into a w2v embedding.
zmirror
The next-gen reverse proxy for full site mirroring