thunlp/LEGENT

Open Platform for Embodied Agents

Language: Python - Size: 1.7 MB - Last synced: 1 day ago - Pushed: 2 days ago - Stars: 117 - Forks: 5

thunlp/OpenHowNet

Core Data of HowNet and OpenHowNet Python API

Language: Python - Size: 259 MB - Last synced: 1 day ago - Pushed: over 2 years ago - Stars: 592 - Forks: 89

thunlp/OpenNRE

An Open-Source Package for Neural Relation Extraction (NRE)

Language: Python - Size: 261 MB - Last synced: 2 days ago - Pushed: 4 months ago - Stars: 4,256 - Forks: 1,055

thunlp/OpenKE

An Open-Source Package for Knowledge Embedding (KE)

Language: Python - Size: 281 MB - Last synced: 2 days ago - Pushed: 4 months ago - Stars: 3,725 - Forks: 984

thunlp/FewRel

A Large-Scale Few-Shot Relation Extraction Dataset

Language: Python - Size: 24.1 MB - Last synced: 1 day ago - Pushed: about 2 years ago - Stars: 718 - Forks: 164

thunlp/Chinese_Rumor_Dataset

中文谣言数据

Size: 53.5 MB - Last synced: 2 days ago - Pushed: almost 4 years ago - Stars: 680 - Forks: 134

thunlp/LAE

Datasets and code for "Fine-Grained Legal Argument-Pair Extraction via Coarse-Grained Pre-training"

Language: Jupyter Notebook - Size: 26.5 MB - Last synced: 4 days ago - Pushed: 4 days ago - Stars: 0 - Forks: 0

thunlp/XQA

Dataset and baseline for ACL 2019 paper "XQA: A Cross-lingual Open-domain Question Answering Dataset"

Language: Python - Size: 43 KB - Last synced: 2 days ago - Pushed: over 2 years ago - Stars: 85 - Forks: 16

thunlp/BERT-KPE

Language: Python - Size: 8.43 MB - Last synced: 3 days ago - Pushed: over 1 year ago - Stars: 438 - Forks: 78

thunlp/Prompt-Transferability

On Transferability of Prompt Tuning for Natural Language Processing

Language: Python - Size: 629 MB - Last synced: 12 days ago - Pushed: 12 days ago - Stars: 87 - Forks: 11

thunlp/GEAR

Source code for ACL 2019 paper "GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification"

Language: Python - Size: 9.4 MB - Last synced: 12 days ago - Pushed: 12 days ago - Stars: 97 - Forks: 25

thunlp/OpenDelta

A plug-and-play library for parameter-efficient-tuning (Delta Tuning)

Language: Python - Size: 42 MB - Last synced: 9 days ago - Pushed: 9 months ago - Stars: 939 - Forks: 76

thunlp/PEVL

Source code for EMNLP 2022 paper “PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models”

Language: Python - Size: 12.7 MB - Last synced: 8 days ago - Pushed: over 1 year ago - Stars: 45 - Forks: 6

thunlp/MatPlotAgent

Language: Python - Size: 19.9 MB - Last synced: 23 days ago - Pushed: about 2 months ago - Stars: 28 - Forks: 3

thunlp/TAADpapers

Must-read Papers on Textual Adversarial Attack and Defense

Language: Python - Size: 173 KB - Last synced: 25 days ago - Pushed: about 1 month ago - Stars: 1,450 - Forks: 192

thunlp/PLMpapers

Must-read Papers on pre-trained language models.

Size: 1.68 MB - Last synced: 24 days ago - Pushed: over 1 year ago - Stars: 3,288 - Forks: 436

thunlp/InfLLM

The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"

Language: Python - Size: 262 KB - Last synced: 25 days ago - Pushed: 26 days ago - Stars: 196 - Forks: 16

thunlp/JointNRE

Joint Neural Relation Extraction with Text and KGs

Language: Python - Size: 259 KB - Last synced: 23 days ago - Pushed: over 1 year ago - Stars: 186 - Forks: 36

thunlp/SememePSO-Attack

Code and data of the ACL 2020 paper "Word-level Textual Adversarial Attacking as Combinatorial Optimization"

Language: Python - Size: 58.7 MB - Last synced: 25 days ago - Pushed: about 3 years ago - Stars: 85 - Forks: 14

thunlp/ERNIE

Source code and dataset for ACL 2019 paper "ERNIE: Enhanced Language Representation with Informative Entities"

Language: Python - Size: 1.45 MB - Last synced: 17 days ago - Pushed: 4 months ago - Stars: 1,401 - Forks: 270

thunlp/THULAC-Java

An Efficient Lexical Analyzer for Chinese

Language: Java - Size: 332 KB - Last synced: 21 days ago - Pushed: over 6 years ago - Stars: 324 - Forks: 114

thunlp/THULAC-Python

An Efficient Lexical Analyzer for Chinese

Language: Python - Size: 78.1 KB - Last synced: 29 days ago - Pushed: over 2 years ago - Stars: 1,962 - Forks: 334

thunlp/ChatEval

Codes for our paper "ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate"

Language: Python - Size: 101 MB - Last synced: 3 months ago - Pushed: 4 months ago - Stars: 160 - Forks: 9

thunlp/THULAC

An Efficient Lexical Analyzer for Chinese

Language: C++ - Size: 93.8 KB - Last synced: 29 days ago - Pushed: 11 months ago - Stars: 769 - Forks: 170

thunlp/LLaVA-UHD

LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images

Language: Python - Size: 2.21 MB - Last synced: about 2 months ago - Pushed: about 2 months ago - Stars: 59 - Forks: 2

thunlp/OpenAttack

An Open-Source Package for Textual Adversarial Attack.

Language: Python - Size: 4.65 MB - Last synced: 30 days ago - Pushed: 10 months ago - Stars: 650 - Forks: 121

thunlp/KRLPapers

Must-read papers on knowledge representation learning (KRL) / knowledge embedding (KE)

Language: TeX - Size: 85 KB - Last synced: about 1 month ago - Pushed: over 2 years ago - Stars: 1,527 - Forks: 249

thunlp/OpenPrompt

An Open-Source Framework for Prompt-Learning.

Language: Python - Size: 14.4 MB - Last synced: about 1 month ago - Pushed: 4 months ago - Stars: 4,132 - Forks: 427

thunlp/UltraChat

Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)

Language: Python - Size: 5.47 MB - Last synced: about 1 month ago - Pushed: 2 months ago - Stars: 2,087 - Forks: 107

thunlp/Knowledge-Plugin

Repo for ACL2023 paper "Plug-and-Play Knowledge Injection for Pre-trained Language Models"

Language: Python - Size: 2.6 MB - Last synced: about 1 month ago - Pushed: about 1 month ago - Stars: 46 - Forks: 3

thunlp/ToolLearningPapers

Size: 13.4 MB - Last synced: about 2 months ago - Pushed: 9 months ago - Stars: 766 - Forks: 42

thunlp/explore-and-evaluate

Code for EMNLP2020 paper "Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment".

Language: Python - Size: 26.4 KB - Last synced: 2 days ago - Pushed: about 2 years ago - Stars: 27 - Forks: 7

thunlp/EREN

Official codes for COLING 2024 paper "Robust and Scalable Model Editing for Large Language Models": https://arxiv.org/abs/2403.17431v1

Language: Python - Size: 1.72 MB - Last synced: about 2 months ago - Pushed: about 2 months ago - Stars: 4 - Forks: 0

thunlp/DeltaPapers

Must-read Papers of Parameter-Efficient Tuning (Delta Tuning) Methods on Pre-trained Models.

Size: 36.1 KB - Last synced: about 1 month ago - Pushed: 11 months ago - Stars: 257 - Forks: 17

thunlp/GNNPapers

Must-read papers on graph neural networks (GNN)

Size: 301 KB - Last synced: about 2 months ago - Pushed: 5 months ago - Stars: 15,439 - Forks: 2,979

thunlp/MuGNN

Source code for ACL2019 paper "Multi-Channel Graph Neural Network for Entity Alignment".

Language: Python - Size: 136 MB - Last synced: 2 days ago - Pushed: over 3 years ago - Stars: 61 - Forks: 11

thunlp/OpenCLaP

Open Chinese Language Pre-trained Model Zoo

Size: 17.6 KB - Last synced: about 1 month ago - Pushed: about 4 years ago - Stars: 972 - Forks: 144

thunlp/Few-NERD

Code and data of ACL 2021 paper "Few-NERD: A Few-shot Named Entity Recognition Dataset"

Language: Python - Size: 67.4 KB - Last synced: about 1 month ago - Pushed: 8 months ago - Stars: 373 - Forks: 56

thunlp/Fast-TransX

An Efficient implementation of TransE and its extended models for Knowledge Representation Learning

Language: C++ - Size: 9.78 MB - Last synced: about 2 months ago - Pushed: over 1 year ago - Stars: 397 - Forks: 109

thunlp/S3Delta

code for paper Sparse Structure Search for Delta Tuning

Language: Jupyter Notebook - Size: 587 KB - Last synced: about 2 months ago - Pushed: over 1 year ago - Stars: 6 - Forks: 2

thunlp/DebugBench

The repository for paper "DebugBench: "Evaluating Debugging Capability of Large Language Models".

Language: Python - Size: 18.2 MB - Last synced: about 2 months ago - Pushed: 4 months ago - Stars: 39 - Forks: 1

thunlp/BMCourse

The repo for Tsinghua summer course: Interdisciplinary Seminar on Big Models

Language: Python - Size: 101 MB - Last synced: about 2 months ago - Pushed: almost 2 years ago - Stars: 258 - Forks: 49

thunlp/PromptPapers

Must-read papers on prompt-based tuning for pre-trained language models.

Size: 194 KB - Last synced: about 2 months ago - Pushed: 10 months ago - Stars: 3,874 - Forks: 367

thunlp/CANE

Source code and datasets of "CANE: Context-Aware Network Embedding for Relation Modeling"

Language: Python - Size: 1.66 MB - Last synced: about 2 months ago - Pushed: about 5 years ago - Stars: 190 - Forks: 77

thunlp/KnowledgeablePromptTuning

kpt code

Language: Python - Size: 211 KB - Last synced: about 2 months ago - Pushed: about 1 year ago - Stars: 196 - Forks: 21

thunlp/THUOCL

THUOCL（THU Open Chinese Lexicon）中文词库

Size: 1.34 MB - Last synced: about 2 months ago - Pushed: about 1 year ago - Stars: 778 - Forks: 189

thunlp/NRLPapers

Must-read papers on network representation learning (NRL) / network embedding (NE)

Language: TeX - Size: 229 KB - Last synced: about 2 months ago - Pushed: almost 4 years ago - Stars: 2,520 - Forks: 652

thunlp/Seq2Seq-Prompt

Source code for COLING 2022 paper "Automatic Label Sequence Generation for Prompting Sequence-to-sequence Models"

Language: Python - Size: 1.52 MB - Last synced: 22 days ago - Pushed: over 1 year ago - Stars: 24 - Forks: 4

thunlp/OpenNE

An Open-Source Package for Network Embedding (NE)

Language: Python - Size: 114 MB - Last synced: about 2 months ago - Pushed: 4 months ago - Stars: 1,668 - Forks: 489

thunlp/CSSReview

This repository contains the paperlist of CSS.

Size: 68.4 KB - Last synced: 2 months ago - Pushed: about 2 years ago - Stars: 25 - Forks: 0

thunlp/EmbodiedAIxLLMPapers

Papers on integrating large language models with embodied AI

Size: 46.9 KB - Last synced: about 2 months ago - Pushed: 5 months ago - Stars: 6 - Forks: 2

thunlp/OpenMatch 📦

An Open-Source Package for Information Retrieval.

Language: Python - Size: 61 MB - Last synced: 3 months ago - Pushed: over 1 year ago - Stars: 443 - Forks: 47

thunlp/HATT-Proto

Code and dataset of AAAI2019 paper Hybrid Attention-Based Prototypical Networks for Noisy Few-Shot Relation Classification

Language: Python - Size: 5.36 MB - Last synced: 2 months ago - Pushed: over 5 years ago - Stars: 180 - Forks: 35

thunlp/SCPapers

Must-read Papers on Sememe Computation

Size: 1.12 MB - Last synced: 3 months ago - Pushed: about 1 year ago - Stars: 191 - Forks: 37

thunlp/attribute_charge

The source code of our COLING'18 paper "Few-Shot Charge Prediction with Discriminative Legal Attributes".

Language: Python - Size: 16.6 KB - Last synced: about 2 months ago - Pushed: over 5 years ago - Stars: 123 - Forks: 29

thunlp/sememe_prediction

Codes for Lexical Sememe Prediction via Word Embeddings and Matrix Factorization (IJCAI 2017).

Language: Python - Size: 39.4 MB - Last synced: 25 days ago - Pushed: over 4 years ago - Stars: 60 - Forks: 25

thunlp/THUCTC

An Efficient Chinese Text Classifier

Language: Java - Size: 1.67 MB - Last synced: 2 months ago - Pushed: over 5 years ago - Stars: 196 - Forks: 67

thunlp/AutoForm

Code for paper "Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication"

Language: Python - Size: 4.73 MB - Last synced: 3 months ago - Pushed: 3 months ago - Stars: 0 - Forks: 0

thunlp/LegalPapers

Must-read Papers on Legal Intelligence

Size: 26.4 KB - Last synced: 3 months ago - Pushed: over 3 years ago - Stars: 443 - Forks: 60

thunlp/Ouroboros

Ouroboros: Speculative Decoding with Large Model Enhanced Drafting

Language: Python - Size: 101 MB - Last synced: 3 months ago - Pushed: 3 months ago - Stars: 10 - Forks: 4

thunlp/COS960

COS960: A Chinese Word Similarity Dataset of 960 Word Pairs

Language: Python - Size: 20.5 KB - Last synced: 25 days ago - Pushed: almost 5 years ago - Stars: 36 - Forks: 2

thunlp/NREPapers

Must-read papers on neural relation extraction (NRE)

Language: TeX - Size: 58.6 KB - Last synced: 3 months ago - Pushed: over 3 years ago - Stars: 1,017 - Forks: 154

thunlp/WantWords

An open-source online reverse dictionary.

Language: JavaScript - Size: 14.5 MB - Last synced: 3 months ago - Pushed: about 2 years ago - Stars: 6,912 - Forks: 620

thunlp/KB2E

Knowledge Graph Embeddings including TransE, TransH, TransR and PTransE

Language: C++ - Size: 63.6 MB - Last synced: 3 months ago - Pushed: over 1 year ago - Stars: 1,373 - Forks: 456

thunlp/TransNet

Source code and datasets of IJCAI2017 paper "TransNet: Translation-Based Network Representation Learning for Social Relation Extraction".

Language: Jupyter Notebook - Size: 153 MB - Last synced: about 2 months ago - Pushed: about 6 years ago - Stars: 103 - Forks: 38

thunlp/NSC

Neural Sentiment Classification

Language: Python - Size: 40 KB - Last synced: 3 months ago - Pushed: about 6 years ago - Stars: 287 - Forks: 96

thunlp/RCPapers

Must-read papers on Machine Reading Comprehension

Size: 16.6 KB - Last synced: 3 months ago - Pushed: almost 4 years ago - Stars: 894 - Forks: 172

thunlp/FalseQA

Repo for ACL2023 paper "Won't Get Fooled Again: Answering Questions with False Premises"

Language: Python - Size: 630 KB - Last synced: about 2 months ago - Pushed: 11 months ago - Stars: 19 - Forks: 0

thunlp/Muffin

Language: Python - Size: 5.93 MB - Last synced: 3 months ago - Pushed: 3 months ago - Stars: 29 - Forks: 2

thunlp/NRE

Neural Relation Extraction, including CNN, PCNN, CNN+ATT, PCNN+ATT

Language: C++ - Size: 234 MB - Last synced: 4 months ago - Pushed: almost 4 years ago - Stars: 813 - Forks: 317

thunlp/Sememe-SC

Source code and data for ACL 2019 paper "Modeling Semantic Compositionality with Sememe Knowledge"

Language: Python - Size: 55.9 MB - Last synced: 25 days ago - Pushed: almost 4 years ago - Stars: 35 - Forks: 7

thunlp/UnifiedInstructionTuning

Language: Python - Size: 1.09 MB - Last synced: 4 months ago - Pushed: 5 months ago - Stars: 2 - Forks: 0

thunlp/CPT

Colorful Prompt Tuning for Pre-trained Vision-Language Models

Language: Python - Size: 19.2 MB - Last synced: 4 months ago - Pushed: over 1 year ago - Stars: 43 - Forks: 1

thunlp/VisualDS

Language: Python - Size: 9.91 MB - Last synced: 4 months ago - Pushed: about 2 years ago - Stars: 25 - Forks: 3

thunlp/OpenQA

The source code of ACL 2018 paper "Denoising Distantly Supervised Open-Domain Question Answering".

Language: Python - Size: 71.3 KB - Last synced: 4 days ago - Pushed: over 5 years ago - Stars: 206 - Forks: 49

thunlp/Moderate-fitting

Language: Python - Size: 8.85 MB - Last synced: 5 months ago - Pushed: 5 months ago - Stars: 3 - Forks: 0

thunlp/IKRL

Image-embodied Knowledge Representation Learning (IJCAI-2017)

Language: C++ - Size: 346 KB - Last synced: 4 months ago - Pushed: over 2 years ago - Stars: 43 - Forks: 10

thunlp/TKRL

Representation Learning of Knowledge Graphs with Hierarchical Types (IJCAI-2016)

Language: C++ - Size: 17.5 MB - Last synced: 4 months ago - Pushed: about 5 years ago - Stars: 79 - Forks: 27

thunlp/RECIPE

Language: Python - Size: 2.48 MB - Last synced: 5 months ago - Pushed: 5 months ago - Stars: 0 - Forks: 0

thunlp/TLNN

Source code for EMNLP-IJCNLP 2019 paper "Event Detection with Trigger-Aware Lattice Neural Network".

Language: Python - Size: 73.2 KB - Last synced: 5 months ago - Pushed: over 4 years ago - Stars: 75 - Forks: 17

thunlp/CKRL

Does William Shakespeare REALLY Write Hamlet? Knowledge Representation Learning with Confidence (AAAI-2018)

Language: C++ - Size: 12.2 MB - Last synced: 4 months ago - Pushed: about 5 years ago - Stars: 44 - Forks: 11

thunlp/WebCPM 📦

Official codes for ACL 2023 paper "WebCPM: Interactive Web Search for Chinese Long-form Question Answering"

Language: HTML - Size: 4.01 MB - Last synced: 6 months ago - Pushed: 6 months ago - Stars: 909 - Forks: 77

thunlp/Chinese_NRE

Source code for ACL 2019 paper "Chinese Relation Extraction with Multi-Grained Information and External Linguistic Knowledge"

Language: Python - Size: 1.5 MB - Last synced: 5 months ago - Pushed: about 4 years ago - Stars: 263 - Forks: 42

thunlp/DeepTHULAC

A High-Performance Lexical Analyzer for Chinese

Language: Python - Size: 139 KB - Last synced: about 1 month ago - Pushed: 6 months ago - Stars: 18 - Forks: 1

thunlp/Modularity-Analysis

Repo for ACL2023 Findings paper "Emergent Modularity in Pre-trained Transformers"

Language: Python - Size: 1.29 MB - Last synced: 6 months ago - Pushed: 11 months ago - Stars: 13 - Forks: 0

thunlp/OOP-THU

OOP Course Material & QA

Size: 19.7 MB - Last synced: 6 months ago - Pushed: about 4 years ago - Stars: 141 - Forks: 18

thunlp/LLM-generated-text-detection

Language: Python - Size: 6.49 MB - Last synced: 6 months ago - Pushed: 6 months ago - Stars: 4 - Forks: 0

thunlp/PL-Marker

Source code for "Packed Levitated Marker for Entity and Relation Extraction"

Language: Python - Size: 1.96 MB - Last synced: 6 months ago - Pushed: about 1 year ago - Stars: 229 - Forks: 36

thunlp/KernelGAT

The source codes for Fine-grained Fact Verification with Kernel Graph Attention Network.

Language: Python - Size: 2.26 MB - Last synced: 6 months ago - Pushed: over 1 year ago - Stars: 166 - Forks: 36

thunlp/LegalPLMs

Source code and checkpoints for legal pre-trained language models.

Language: Python - Size: 30.3 KB - Last synced: 6 months ago - Pushed: about 3 years ago - Stars: 147 - Forks: 22

thunlp/NLP-THU

NLP Course Material & QA

Size: 69.3 KB - Last synced: 6 months ago - Pushed: about 2 years ago - Stars: 158 - Forks: 22

thunlp/DocRED

Dataset and codes for ACL 2019 DocRED: A Large-Scale Document-Level Relation Extraction Dataset.

Language: Python - Size: 55.7 KB - Last synced: 7 months ago - Pushed: over 3 years ago - Stars: 572 - Forks: 107

thunlp/CAIL2018

Language: Python - Size: 41 KB - Last synced: 6 months ago - Pushed: almost 6 years ago - Stars: 109 - Forks: 45

thunlp/SOS4NLP

Survey of Surveys for Natural Language Processing (SOS4NLP)

Size: 162 KB - Last synced: 6 months ago - Pushed: almost 3 years ago - Stars: 327 - Forks: 40

thunlp/HMEAE

Source code for EMNLP-IJCNLP 2019 paper "HMEAE: Hierarchical Modular Event Argument Extraction".

Language: Python - Size: 44.9 KB - Last synced: 7 months ago - Pushed: about 2 years ago - Stars: 84 - Forks: 21

thunlp/MetaAdaptRank

Code and data of the ACL 2021 paper: Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision

Language: Python - Size: 55.3 MB - Last synced: 7 months ago - Pushed: over 2 years ago - Stars: 7 - Forks: 2

thunlp/PathNRE

Source code and dataset of EMNLP2017 paper "Incorporating Relation Paths in Neural Relation Extraction".

Language: C++ - Size: 245 KB - Last synced: 7 months ago - Pushed: over 4 years ago - Stars: 41 - Forks: 11

thunlp/SelectiveMasking

Source code for "Train No Evil: Selective Masking for Task-Guided Pre-Training"

Language: Python - Size: 2.01 MB - Last synced: 7 months ago - Pushed: over 1 year ago - Stars: 67 - Forks: 15

thunlp/MNRE

The code and data for ACL2017 paper "Neural Relation Extraction with Multi-lingual Attention"

Language: C++ - Size: 20.5 KB - Last synced: 7 months ago - Pushed: about 7 years ago - Stars: 45 - Forks: 17

thunlp/TensorFlow-Summarization

Language: Python - Size: 851 KB - Last synced: 6 months ago - Pushed: over 6 years ago - Stars: 391 - Forks: 112