Siyu WANG's repositories
_ProjetM2_Optimus
Projet pour cours Documents Structurés TAL INALCO M2
Project_CNN
For projet CNN TAL M2 Inalco
Projet_Encadr-_BAO
Projet réalisé en M1 avec différentes boîtes à outil de NLP
Projet_python_lexicostats_interface
Project in python creating an program with user interface to detect language, proceed tokennization and POS tagging, and show statistic information of the input corpus
Projet_scrapy_visualisation
Projet scrapy et visualisation des données
awesome_Chinese_medical_NLP
中文医学NLP公开资源整理：术语集/语料库/词向量/预训练模型/知识图谱/命名实体识别/QA/信息抽取/模型/论文/etc
bert-relation-classification
A pytorch implementation of BERT-based relation classification
BullshitGenerator
Needs to generate some texts to test if my GUI rendering codes good or not. so I made this.
chinese-poetry
The most comprehensive database of Chinese poetry 🧶最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。
documents-structures
Cours du M2 Ingénierie Multilingue (Inalco)
ECDICT
Free English to Chinese Dictionary Database
fixme
An practice repo for cloning, fixing, comitting and making a PR
IndexInverse
Inverse Index projet in Python by Siyu WANG and Natia DAVITASHVILI
LightTagger
LightTagger is an ultra-lightweight open-source text annotation tool, which can be widely used for manual auxiliary annotation tasks mining such as named entities, entity relationships, and events in text data.
models
Models and examples built with TensorFlow
nlp_course
YSDA course in Natural Language Processing
nndl.github.io
《神经网络与深度学习》 邱锡鹏著 Neural Network and Deep Learning
PaddleNLP
NLP Core Library and Model Zoo based on PaddlePaddle 2.0
pelican
Static site generator that supports Markdown and reST syntax. Powered by Python.
projet_XML_exos
Projet réalisé en M1, page entièrement codé en XML avec un feuille de style xslt
rasa_chatbot_cn
building a chinese dialogue system based on the newest version of rasa(基于最新版本rasa搭建的对话系统)
spacy-ner-annotator
Train Spacy ner with custom dataset
text_summarization
various ways to summarize text and for multiple languages using Python Library. Created on 13 Mar 2018
The-NLP-Pandect
A comprehensive reference for all topics related to Natural Language Processing
wav2letter
Facebook AI Research's Automatic Speech Recognition Toolkit
weibo-crawler
新浪微博爬虫，用python爬取新浪微博数据，并下载微博图片和微博视频
Wordless
An Integrated Corpus Tool with Multi-Language Support for the Study of Language, Literature, and Translation