Radar Station Supplementary Material 1/2

# Radar Station data file. 

 This repo contains the data necessary for the paper 'Radar Station: Using KG Embeddings for Semantic Table Interpretation and Entity Disambiguation.'

The second part of the data is available at https://zenodo.org/record/6522921

 Its structure of it is as follows:

 '''
 ├─readme.md
 ├─DAGOBAHSL_Scoring
 │  ├─Limaye_Result
 │  ├─T2D_Result
 │  ├─2T_Result
 │  ├─ShortTable_Result
 ├─Embeddings
 │  ├─RotetE
 │  ├─ComplEx
 │  ├─TransE
 │  ├─Dismult
 ├─Datasets
 │  ├─Key_Column_Index
 │  │  ├─Limaye
 │  │  ├─T2D
 │  ├─ShortTable
 ├─Wikidata_Ground_Truth
 │  ├─Wikidata_GS_Limaye
 │  ├─Wikidata_GS_T2D
 │  ├─Wikidata_GS_2T
 │  ├─Wikidata_GS_ShortTable
 '''

## DAGOBAHSL_Scoring
 It contains the result of the candidate scoring step after the four datasets were processed through a previous annotation system.
 In this score step, we did not filter any candidates during the calculation and always kept their scores. 

## Embeddings

 This folder contains four embeddings used during our experiment.
 We provide four embeddings for the experiments: TransE, RotatE, Dismult, and ComplEx. 
 In which the RotatE embeddings are from the pre-trained embeddings of GraphVite: https://graphvite.io/docs/latest/pretrained_model.html 
 TransE, Dismult, and ComplEx are trained using Pytorch-BigGraph with Wikidata dump version 2021 May.

**NOTICE**: the Dismult and ComplEx Embeddings should be further added to this folder.

## Datasets
### Key_Column_Index

 Key_Column_Index folder contains the index of the key column position for T2D and Limaye that are manually annotated.
 It tells Radar Station in which column we should run.

### ShortTable

 It contains the ShortTable dataset with tables of only two rows.

## Wikidata_Ground_Truth
 It contains the ground truth of the four datasets with Wikidata entities.