adienxy's starred repositories

shap

A game theoretic approach to explain the output of any machine learning model.

Language:Jupyter NotebookLicense:MITStargazers:22269Issues:239Issues:2496

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

Language:PythonLicense:Apache-2.0Stargazers:14610Issues:135Issues:2085

longformer

Longformer: The Long-Document Transformer

Language:PythonLicense:Apache-2.0Stargazers:2013Issues:42Issues:228

hedwig

PyTorch deep learning models for document classification

Language:PythonLicense:Apache-2.0Stargazers:590Issues:20Issues:44

bert_for_longer_texts

BERT classification model for processing texts longer than 512 tokens. Text is first divided into smaller chunks and after feeding them to BERT, intermediate results are pooled. The implementation allows fine-tuning.

Language:PythonLicense:NOASSERTIONStargazers:110Issues:5Issues:16

chinese-bigbird

中文bigbird预训练模型

Language:PythonLicense:Apache-2.0Stargazers:83Issues:3Issues:9

taylor-series-linear-attention

Explorations into the recently proposed Taylor Series Linear Attention

Language:PythonLicense:MITStargazers:83Issues:2Issues:3

HMT-pytorch

Official Implementation of "HMT: Hierarchical Memory Transformer for Long Context Language Processing"

Language:PythonLicense:Apache-2.0Stargazers:53Issues:2Issues:3

MJP

An official Pytorch implementation of "Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers", CVPR 2023.

Language:PythonLicense:MITStargazers:38Issues:3Issues:0

TextSSL

[AAAI 2022] Sparse Structure Learning via Graph Neural Networks for Inductive Document Classification

Language:PythonLicense:MITStargazers:31Issues:3Issues:4

kanformer

Naively combining transformers and Kolmogorov-Arnold Networks to learn and experiment

Language:PythonLicense:MITStargazers:24Issues:3Issues:0

RAN

RAN: Recurrent Attention Networks for Long-text Modeling | Findings of ACL23

Language:PythonLicense:MITStargazers:20Issues:2Issues:1

Graphormer

Do Transformers Really Perform Bad for Graph Representation? [NIPS-2021]

Language:PythonStargazers:18Issues:1Issues:0

DHGAS

Implementation codes for AAAI23 paper "Dynamic Heterogeneous Graph Attention Neural Architecture Search"

Language:PythonStargazers:8Issues:1Issues:0

KANFormer

Optimized -KAN-based Transformer Models Performance Test on Various Tasks (Point cloud&Vision)

littlebird

Implementation of LittleBird: Efficient Faster & Longer Transformer for Question Answering

Language:PythonLicense:MITStargazers:4Issues:3Issues:0
Language:PythonStargazers:3Issues:1Issues:0

FakeNewsData

Fake news detection dataset

Language:PythonStargazers:3Issues:0Issues:0

long-text-classification-model

implement longformer, bigbird

Language:Jupyter NotebookStargazers:2Issues:1Issues:0

HMIGCN

A Framework for Long Document Classification

Language:PythonStargazers:2Issues:1Issues:0

AESC

The aspect sentiment classification (AESC) task includes aspect terms extraction (AE) and aspect terms sentiment analysis (ASC).

Language:PythonStargazers:2Issues:2Issues:0

Explainable-AI-XAI-

Text LRP, Grad-CAM, Darkon, Lime and Shap

Language:Jupyter NotebookStargazers:1Issues:1Issues:0

MBTI_Predictor_Using_Several_Methods

Model fine tuned with BigBird is included

Language:PythonStargazers:1Issues:1Issues:0
Language:PythonStargazers:1Issues:1Issues:0