THUNLP
- FIT Building, Tsinghua University, Beijing
- http://nlp.csai.tsinghua.edu.cn
- thunlp@gmail.com
Pinned repositories
Repositories
-
CSS-LM
CSS-LM: Contrastive Semi-supervised Fine-tuning of Pre-trained Language Models
-
-
OpenAttack
An Open-Source Package for Textual Adversarial Attack.
-
TAADpapers
Must-read Papers on Textual Adversarial Attack and Defense
-
COVID19-CountryImage
Dataset of China's-image-related tweets during COVID-19 with aspect-level sentiment labels.
-
-
-
FewRel
A Large-Scale Few-Shot Relation Extraction Dataset
-
ERNIE
Source code and dataset for ACL 2019 paper "ERNIE: Enhanced Language Representation with Informative Entities"
-
KernelGAT
The source codes for Fine-grained Fact Verification with Kernel Graph Attention Network.
-
-
LegalPapers
Must-read Papers on Legal Intelligence
-
-
DSDocRE
Source code for EMNLP 2020 paper "Denoising Relation Extraction from Document-level Distant Supervision"
-
PLMpapers
Must-read Papers on pre-trained language models.
-
ConversationQueryRewriter
Code and Data for SIGIR 2020 Paper "Few-Shot Generative Conversational Query Rewriting"
-
OpenHowNet
Core Data of HowNet and OpenHowNet Python API
-
WantWords
An open-source online reverse dictionary.
-
SememePSO-Attack
Code and data of the ACL 2020 paper "Word-level Textual Adversarial Attacking as Combinatorial Optimization"
-
SememeWSD
Code and data for the COLING 2020 paper "Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet"
-
DocRED
Dataset and codes for ACL 2019 DocRED: A Large-Scale Document-Level Relation Extraction Dataset.