Pinned Repositories
DCL
Code for the CICAI 2021 paper "Disentangled Contrastive Learning for Learning Robust Textual Representations".
Deep-Transfer-Learning
Deep Transfer Learning Papers
Diaformer
Diaformer: Automatic Diagnosis via Symptoms Sequence Generation
DiagnoseAdv
Source code for the IJCKG2021 paper "Normal vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extraction".
IEDatasets
Information extraction dataset zoo.
LegalPP
Source code and dataset for the CCKS2021 paper "Text-guided Legal Knowledge Graph Reasoning".
Low-resource_KBP
Some papers on low-resource knowledge base population. (mostly from 2018 to 2020)
MTM
MTM
OpenUE
An Open-Source Package for Universal Extraction (UE)
papers-on-neural-relation-extraction
zxlzr's Repositories
zxlzr/DART
zxlzr/MarkTool
MarkTool是一款基于web的开源通用文本标注工具,支持大规模实体标注、关系标注、事件标注、文本分类、基于字典匹配和正则匹配的自动标注以及用于实现归一化的标准名标注,同时也支持文本的迭代标注和实体的嵌套标注。标注规范可自定义且同类型任务中可“一次创建多次复用”。通过分级实体集合扩大了实体类型的规模,并设计了全新高效的标注方式,提升了用户体验和标注效率。此外,MarkTool增加了审核环节,可对多人的标注结果进行一致性检验和调整,提高了标注语料的准确率和可靠性。
zxlzr/Semantic-Parsing
zxlzr/SENTA
Code and dataset for the paper "Interventional Aspect-Based Sentiment Analysis".
zxlzr/aquvitae
The Easiest Knowledge Distillation Library for Lightweight Deep Learning
zxlzr/BalancedGroupSoftmax
CVPR 2020 oral paper: Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax.
zxlzr/bert_seq2seq
pytorch实现bert做seq2seq任务,使用unilm方案,现在也可以做文本分类,情感分析,NER,词性标注等任务。
zxlzr/ChineseEHRBert
A Chinese EHR Bert Pretrained Model.
zxlzr/ChineseSemanticKB
ChineseSemanticKB,chinese semantic knowledge base, 面向中文处理的12类、百万规模的语义常用词典,包括34万抽象语义库、34万反义语义库、43万同义语义库等,可支持句子扩展、转写、事件抽象与泛化等多种应用场景。
zxlzr/CycleGT
code of CycleGT
zxlzr/doing_the_PhD
zxlzr/entity-embed
PyTorch library for transforming entities like companies, products, etc. into vectors to support scalable Record Linkage / Entity Resolution using Approximate Nearest Neighbors.
zxlzr/eventnative
EventNative is an open-source data collection framework
zxlzr/knodle
A PyTorch-based open-source framework that provides methods for improving the weakly annotated data and allows researchers to efficiently develop and compare their own methods.
zxlzr/L2R2
PyTorch implementation of L2R2 in SIGIR 2020
zxlzr/large-scale-oie
zxlzr/Low-ResourceKBPPapers
Paper List of Low-Resource Knowledge Base Population
zxlzr/Low_Resource_KBP
knowledge graph population in low resource conditions
zxlzr/nlpcda
一键中文数据增强包 ;中文EDA; NLP数据增强、NER数据增强 :pip install nlpcda
zxlzr/OpenAttack
An Open-Source Package for Textual Adversarial Attack.
zxlzr/prancer
Platform enabling Rapid Annotation for Clinical Entity Recognition
zxlzr/PURE
Code and models for the paper "A Frustratingly Easy Approach for Entity and Relation Extraction"
zxlzr/pykeen
A Python library for learning and evaluating knowledge graph embeddings
zxlzr/PyTorch-BYOL
PyTorch implementation of Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
zxlzr/SemEval2021Task4
The 4th rank system of the SemEval 2021 Task4.
zxlzr/skweak
skweak: A software toolkit for weak supervision applied to NLP tasks
zxlzr/spikex
SpikeX - SpaCy Pipes for Knowledge Extraction
zxlzr/token2index
A lightweight but powerful library to build token indices for NLP tasks, compatible with major Deep Learning frameworks like PyTorch and Tensorflow.
zxlzr/transformers-data-augmentation
Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper
zxlzr/xf_event_extraction2020Top1
科大讯飞2020事件抽取挑战赛第一名解决方案&完整事件抽取系统