Name: 纪焘 (Tao Ji)
Type: User
Company: @AntNLP @ECNU-CS
Bio: My name is Tao, I am an artist, a programming artist, I am hired for people to profile their fantasies, their deep learning fantasies.
Location: Shanghai, China
Blog: http://taoji.site
纪焘 (Tao Ji)'s Projects
This is the code I wrote at the time of preparation ACM contest.
An open-source NLP research library, built on PyTorch.
C++ Neural Network Expansion Library on Dynet for AntNLP Group.
AntNLP's cross-domain dependency parser at CCL2021 shared task.
Universal data IO module in NLP tasks (for AntNLP Group)
An implementation of "Deep Biaffine Attention for Neural Dependency Parsing"
DeNSe parser in Dependency Parsing as Head Selection (EACL 2017) https://arxiv.org/abs/1606.01280
DyNet: The Dynamic Neural Network Toolkit
East China Normal University Parser
ECNU NLP group reads ACL17 paper in the form of seminars in the 2017 summer.
ECNU NLP group learns CS224n in the form of seminars in the 2017 summer.
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
fastNLP: A Modularized and Extensible Toolkit for Natural Language Processing. Currently still in incubation.
CoNLL18 Multilingual dataset for Graph Neural Networks Dependency Parser
Hugo + PaperMod + Github Action
Ushio's Blog
My git note repository.
When I read, I did some notes.
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
Second-Order Semantic Dependency Parsing with End-to-End Neural Networks
Home Page
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
An unstable, still under construction, but updated version of the Parser repo, used for Stanford's submission in the CoNLL17 shared task.
eXtensible Neural Machine Translation