zxlzr

DART

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。

Semantic-Parsing

SENTA

Code and dataset for the paper "Interventional Aspect-Based Sentiment Analysis".

aquvitae

The Easiest Knowledge Distillation Library for Lightweight Deep Learning

BalancedGroupSoftmax

CVPR 2020 oral paper: Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax.

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。

ChineseEHRBert

A Chinese EHR Bert Pretrained Model.

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。

CycleGT

code of CycleGT

doing_the_PhD

entity-embed

PyTorch library for transforming entities like companies, products, etc. into vectors to support scalable Record Linkage / Entity Resolution using Approximate Nearest Neighbors.

eventnative

EventNative is an open-source data collection framework

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.

L2R2

PyTorch implementation of L2R2 in SIGIR 2020

large-scale-oie

Low-ResourceKBPPapers

Paper List of Low-Resource Knowledge Base Population

Low_Resource_KBP

knowledge graph population in low resource conditions

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

OpenAttack

An Open-Source Package for Textual Adversarial Attack.

prancer

Platform enabling Rapid Annotation for Clinical Entity Recognition

PURE

Code and models for the paper "A Frustratingly Easy Approach for Entity and Relation Extraction"

pykeen

A Python library for learning and evaluating knowledge graph embeddings

PyTorch-BYOL

PyTorch implementation of Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning

SemEval2021Task4

The 4th rank system of the SemEval 2021 Task4.

skweak

skweak: A software toolkit for weak supervision applied to NLP tasks

spikex

SpikeX - SpaCy Pipes for Knowledge Extraction

token2index

A lightweight but powerful library to build token indices for NLP tasks, compatible with major Deep Learning frameworks like PyTorch and Tensorflow.

transformers-data-augmentation

Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper

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