Errol W. Mamani

errol.mamani@ucsp.edu.pe

wildr.10@gmail.com

Arequipa, Peru

I am a prospective Ph.D. student in Computer Science, actively collaborating with the NLP research community. I volunteered at Cohere for AI as a beginner researcher,and assisted with the AYA prompt data in the past, I also was co-chair the LX NLP Workshop co-located with NAACL 2024. Later, I have been working as a ML-Computer vision Engineer at Ping4All and after that as AI engineer at Crown,I also have a background in natural language processing and a broad research interests focus NLP and computational social science.

Previously, I worked with Professor Jose E. Ochoa, at the Research and Innovation Center in Computer Science Labs in Peru, focusing on deep learning methods to detect aggressive or offensive content in social media in 2022. I have also volunteered and participated in key events, such as the IISPDL 2019, Khipu 2019, Latinx in AI at NeurIPS 2019 and 2020, the TRAC 2020 Workshop, and the Mexican NLP Summer School 2021 for further info check my CV.

news

Jan 08, 2026	Read about my recent talk in here
Jan 05, 2026	I am pursuing job opportunities & preparing for a PhD applications!
Nov 10, 2024	My hosting experience of the LxAI workshop @NAACL24.

selected publications

vgcnbert
Aggressive language detection using vgcn-bert for spanish texts

Errol Mamani-Condori, and José Ochoa-Luna

In Brazilian Conference on Intelligent Systems , 2021

Abs Bib HTML PDF Video

The increasing influence from users in social media has made that aggressive content disseminates over the internet. To tackle this problem, recent advances in Aggressive Language Detection have demonstrated a good performance of Deep Learning techniques. Recently Transformer based architectures such as Bidirectional Encoder Representations from Transformer (BERT) outperformed previous aggressive text detection baselines. However, most of the Transformers-based approaches are unable to properly capture global information such as language vocabulary. Thus, in this work, we focus on aggressive content detection using the combination of Vocabulary Graph Convolutional Network (VGCN) to capture global information and BERT to model local information.
@inproceedings{mamani2021aggressive, title = {Aggressive language detection using vgcn-bert for spanish texts}, author = {Mamani-Condori, Errol and Ochoa-Luna, Jos{\'e}}, booktitle = {Brazilian Conference on Intelligent Systems}, pages = {359--373}, year = {2021}, organization = {Springer}, url = {http://link.aps.org/doi/10.1103/PhysRev.47.777}, }