Imperial College London
Dr Felipe Orihuela-Espina

DrFelipeOrihuela-Espina

Faculty of Medicine, Department of Surgery & Cancer

Honorary Lecturer
 
 
 
//

Contact

 

f.orihuela-espina

 
 
//

Location

 

//

Summary

 

Publications

Citation

BibTex format

@article{Garcia-Mendoza:2022:10.3233/JIFS-219241,
author = {Garcia-Mendoza, J-L and Villasenor-Pineda, L and Orihuela-Espina, F and Bustio-Martinez, L},
doi = {10.3233/JIFS-219241},
journal = {Journal of Intelligent and Fuzzy Systems},
pages = {4523--4529},
title = {An autoencoder-based representation for noise reduction in distant supervision of relation extraction},
url = {http://dx.doi.org/10.3233/JIFS-219241},
volume = {42},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Distant Supervision is an approach that allows automatic labeling of instances. This approach has been used in Relation Extraction. Still, the main challenge of this task is handling instances with noisy labels (e.g., when two entities in a sentence are automatically labeled with an invalid relation). The approaches reported in the literature addressed this problem by employing noise-tolerant classifiers. However, if a noise reduction stage is introduced before the classification step, this increases the macro precision values. This paper proposes an Adversarial Autoencoders-based approach for obtaining a new representation that allows noise reduction in Distant Supervision. The representation obtained using Adversarial Autoencoders minimize the intra-cluster distance concerning pre-trained embeddings and classic Autoencoders. Experiments demonstrated that in the noise-reduced datasets, the macro precision values obtained over the original dataset are similar using fewer instances considering the same classifier. For example, in one of the noise-reduced datasets, the macro precision was improved approximately 2.32% using 77% of the original instances. This suggests the validity of using Adversarial Autoencoders to obtain well-suited representations for noise reduction. Also, the proposed approach maintains the macro precision values concerning the original dataset and reduces the total instances needed for classification.
AU  - Garcia-Mendoza,J-L
AU  - Villasenor-Pineda,L
AU  - Orihuela-Espina,F
AU  - Bustio-Martinez,L
DO  - 10.3233/JIFS-219241
EP  - 4529
PY  - 2022///
SN  - 1064-1246
SP  - 4523
TI  - An autoencoder-based representation for noise reduction in distant supervision of relation extraction
T2  - Journal of Intelligent and Fuzzy Systems
UR  - http://dx.doi.org/10.3233/JIFS-219241
UR  - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000777901700021&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=a2bf6146997ec60c407a63945d4e92bb
UR  - https://content.iospress.com/articles/journal-of-intelligent-and-fuzzy-systems/ifs219241
VL  - 42
ER  -
Download