KGCode Lab, Southeast University

MELBench

Multimodal entity linking (MEL) aims to utilize multimodal information to map mentions to corresponding entities defined in knowledge bases. We release three MEL datasets: Weibo-MEL, Wikidata-MEL and Richpedia-MEL, containing 25,602, 18,880 and 17,806 samples from social media, encyclopedia and multimodal knowledge graphs respectively. A MEL dataset construction approach is proposed, including five stages: multimodal information extraction, mention extraction, entity extraction, triple construction and dataset construction. Experiment results demonstrate the usability of the datasets and the distinguishability between baseline models.

FastRE

The code and dataset for "FastRE: Towards Fast Relation Extraction with Convolutional Encoder and Improved Cascade Binary Tagging Framework"

MEL-GHMFC

PAAR

FEED

MGRE

Multi-Granularity Neural Networks for Document-Level Relation Extraction

pasCore

PasCore: A Chinese Overlapping Relation Extraction Model based on Global Pointer Annotation Strategy

ACQD

ASKRL

BalCompress

BalCompress: model compression with open-domain unlabeled data for named entity recognition

KEEN

This repository contains our implementation of paper Hyperbolic Knowledge Graph Embedding in Extended Poincaré Ball. Xingchen Zhou, Peng Wang, Zhe Pan.

LaTex4SEU

This is a LaTex template for Southeast University.

kgcode-tab

MDM