THUNLP

PLMpapers

Must-read Papers on pre-trained language models.

KB2E

Knowledge Graph Embeddings including TransE, TransH, TransR and PTransE

TensorFlow-TransX

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

OpenMatch

An Open-Source Package for Information Retrieval.

BERT-KPE

Fast-TransX

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

BMCourse

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

JointNRE

Joint Neural Relation Extraction with Text and KGs

KernelGAT

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

PTR

Prompt Tuning with Rules

RE-Context-or-Names

Bert-based models(BERT, MTB, CP) for relation extraction.

SelectiveMasking

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

CorefBERT

Source code for EMNLP 2020 paper "Coreferential Reasoning Learning for Language Representation"

QuoteR

Official code and data of the ACL 2022 paper "QuoteR: A Benchmark of Quote Recommendation for Writing"

CPT

Colorful Prompt Tuning for Pre-trained Vision-Language Models

PELT

Source code for "A Simple but Effective Pluggable Entity Lookup Table for Pre-trained Language Models"

PEVL

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

TR-BERT

Source code for NAACL 2021 paper "TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference"

StyleAttack

Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"

HiddenKiller

Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"

Seq2Seq-Prompt

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

Intrinsic-Prompt-Tuning

DPT

thunlp.github.io

Unified-DeltaTuning

FastPromptTuning

Source code for Findings of EMNLP 2022 paper "FPT: Improving Prompt Tuning Efficiency via Progressive Training"”

Mode-Connectivity-PLM

S3Delta

code for paper Sparse Structure Search for Delta Tuning

AdversarialTaboo

MSGI

Official code and data of the Findings of ACL 2022 paper "Sememe Prediction for BabelNet Synsets using Multilingual and Multimodal Information"