Name: Yu Zhang
Type: User
Company: Soochow University
Bio: PhD student @SUDA-LA; NLP/CL/ML; ๐
Twitter: yzhang_cs
Location: Shenzhen, Guangdong
Blog: https://yzhang.site
Yu Zhang's Projects
A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
C++ Library
Conditional Random Field
[ACL'20, IJCAI'20] Code for "Efficient Second-Order TreeCRF for Neural Dependency Parsing" and "Fast and Accurate Neural CRF Constituency Parsing".
[COLING'22] Code for "Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments".
[EMNLP'23] Code for "Non-autoregressive Text Editing with Copy-aware Latent Alignments".
Hidden Markov Model
ๅบไบๆ ๅฝขๆกไปถ้ๆบๅบ็้ซ้ถๅฅๆณๅๆ
:rocket: State-of-the-art parsers for natural language.
Several models for POS Tagging
Fast, general, and tested differentiable structured prediction in PyTorch
A flask-based cbir system
Source code of "Headed Span-Based Projective Dependency Parsing" and "Combining (second-order) graph-based and headed span-based projective dependency parsing
Style guides for Google-originated open-source projects
Sequence Labeling models
Official Implementation of ACL2023: Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars
source code of NAACL2021 "PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbolsโ and ACL2021 main conference "Neural Bilexicalized PCFG Induction"
Development repository for the Triton language and compiler
Implementation of a Transformer, but completely in Triton
Understand and test language model architectures on synthetic tasks.