tangminji Goto Github PK

aser

ASER (Activities, States, Events, and their Relations): a large-scale weighted eventuality knowledge graph.

cs-notes

:books: 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计

discrimloss

DiscrimLoss: A Universal Loss for Hard Samples and Incorrect Samples Discrimination

evals

Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.

google-research

Google Research

la-beginner

lhy_machine_learning

李宏毅2021春季机器学习课程课件及作业

ltp

Language Technology Platform

math-world

megatron-lm

Ongoing research training transformer models at scale

mentormix_pytorch

[MentorMix] "Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels" implemented in the PyTorch version.

ml2021-spring

李宏毅 (Hung-Yi Lee) 機器學習 Machine Learning 2021 Spring

ner_demo

按要求制作的ner_demo，后端暂时使用ltp获取结果，目前先使用固定的两个样例展示，

noisywikihow

NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language Processing (ACL2023 Findings)

noisywikihow-dataset

NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language Processing (ACL2023 Findings)

office-e5

Office E5 订阅，使用Github Action 自动调用API。By Java

openai-python

The OpenAI Python library provides convenient access to the OpenAI API from applications written in the Python language.

paddle-nmt

saved models

plm-nlp-code

scir-training-day

a small training program for new crews of HIT-SCIR

stgn-noisyner

Sub-experiment of "STGN: an Implicit Regularization Method for Learning with Noisy Labels in Natural Language Processing" (EMNLP 2022) by Tingting Wu, Xiao Ding, Minji Tang, Hao Zhang, Bing Qin, Ting Liu.

stgn-sst

STGN: an Implicit Regularization Method for Learning with Noisy Labels in Natural Language Processing (EMNLP 2022)

stgn-wikihow

Sub-experiment of "STGN: an Implicit Regularization Method for Learning with Noisy Labels in Natural Language Processing" (EMNLP 2022) by Tingting Wu, Xiao Ding, Minji Tang, Hao Zhang, Bing Qin, Ting Liu.

tangminji.github.io

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.