IberLEF 2022
Iberian Languages Evaluation Forum 2022

Table of Contents

• Preface
  Summary: There were 91 papers submitted for the 10 shared tasks. All 91 submissions were accepted. These papers describe the participation of around 150 research groups from 24 countries, in 10 different NLP tasks.
• Organization
  
• IberLEF 2022 Overview: Natural Language Processing for Iberian Languages
  Julio Gonzalo, Manuel Montes-y-Gómez, Francisco Rangel

Aspect-Based Sentiment Analysis in Portuguese (ABSAPT)

• Deep Learning Brasil at ABSAPT 2022: Portuguese Transformer Ensemble Approaches
  Juliana Resplande Sant’Anna Gomes, Eduardo Augusto Santos Garcia, Adalberto Ferreira Barbosa Junior, Ruan Chaves Rodrigues, Diogo Fernandes Costa Silva, Dyonnatan Ferreira Maia, Nádia Félix Felipe da Silva, Arlindo Rodrigues Galvão Filho, Anderson da Silva Soares
• NILC at ABSAPT 2022: Aspect Extraction for Portuguese
  Mateus Tarcinalli Machado, Thiago Alexandre Salgueiro Pardo
• Team PiLN at ABSAPT 2022: Lexical and BERT Strategies for Aspect-Based Sentiment Analysis in Portuguese
  Francisco Assis Ricarte Neto, Rogério Figueredo de Sousa, Roney Lira de Sales Santos, Rafael Torres Anchiêta, Raimundo Santos Moura
• TeamUFPR at ABSAPT 2022: Aspect Extraction with CRF and BERT
  Tiago Heinrich, Felipe Marchi
• UFSCar’s Team at ABSAPT 2022: Using Syntax, Semantics and Context for Solving the Tasks
  Fernanda Malheiros Assi, Gabriel Barbosa Candido, Lucas Nildaimon dos Santos Silva, Diego Furtado Silva, Helena de Medeiros Caseli

Spanish Author Profiling for Political Ideology (PoliticEs)

• LosCalis at PoliticEs 2022: Political Author Profiling using BETO and MarIA
  Sergio Santamaria Carrasco, Roberto Cuervo Rosillo
• NLP-CIMAT at PoliticEs 2022: PolitiBETO, a Domain-Adapted Transformer for Multi-class Political Author Profiling
  Emilio Villa−Cueva, Ivan González−Franco, Fernando Sanchez−Vega, Adrián Pastor López−Monroy
• Alejandro Mosquera at PoliticEs 2022: Towards Robust Spanish Author Profiling and Lessons Learned from Adversarial Attacks
  Alejandro Mosquera
• CIMAT_2021 at PoliticEs 2022: Ensemble Based Classification Algorithms for Author Profiling in Spanish Language
  Enrique Santibáñez−Cortés, Azael Carrillo−Cabrera, Yair Antonio Castillo−Castillo, Daniela Moctezuma, Victor Muñiz−Sánchez
• HalBERT at PoliticEs 2022: Are Machine Learning Algorithms better for Author Profiling?
  Cristina García Holgado, Aman Sinha
• I2C at PoliticEs 2022: Using Transformers to Identify Political Ideology in Spanish Tweets
  Pablo Cáceres Ramos, Jacinto Mata Vázquez, Victoria Pachón Álvarez, Juan Luis Domínguez Olmedo
• TeamMX at PoliticEs 2022: Analysis of Feature Sets in Spanish Author Profiling for Political Ideology
  José Luis Ochoa−Hernández, Yuridiana Alemán
• UniRetro at PoliticEs@IberLef 2022: Political Ideology Profiling using Language Models
  Andrei−Alexandru Manea, Liviu Petrişor Dinu
• UNED at PoliticEs 2022: Testing Approximate Nearest Neighbors and Spanish Language Models for Author Profiling in Political Ideology
  Alvaro Rodrigo, Hermenegildo Fabregat, Roberto Centeno
• THANGCIC at PoliticEs 2022: Term-based BERT for Extracting Political Ideology from Spanish Author Profiling
  Hoang Thang Ta, Abu Bakar Siddiqur Rahman, Lotfollah Najjar, Alexander Gelbukh
• URJC-Team at PoliticEs 2022: Political Ideology Prediction using Linear Classifiers
  Miguel Ángel Rodríguez−García, Soto Montalvo Herranz, Raquel Martínez Unanue
• SINAI at PoliticEs 2022: Exploring Relative Frequency of Words in Stylometrics for Profile Discovery
  César Espin−Riofrio, Jenny Ortiz−Zambrano, Arturo Montejo−Ráez
• UC3MDeep at PoliticEs 2022: Exploring Traditional Machine Learning Algorithms for Political Ideology Detection
  Álvaro García−Ochoa Martín−Forero, Alejandro Massotti López, Isabel Segura−Bedmar
• INFOTEC−LaBD at PoliticES 2022: Low−dimensional Stacking Model for Political Ideology Profiling
  Hiram Cabrera, Eric S. Tellez, Sabino Miranda

Recommendation System, Sentiment Analysis and Covid Semaphore Prediction for Mexican Tourist Texts (Rest-Mex 2022)

• The Winning Approach for the Recommendation Systems Shared Task @REST_MEX 2022
  Cipriano Callejas−Hernández, Erika Rivadeneira−Pérez, Fernando Sánchez−Vega, Adrián Pastor López−Monroy, Esaú Villatoro−Tello
• A Hybrid Recommender Model based on Information Retrieval for Mexican Tourism Text in Rest-Mex 2022
  Victor Giovanni Morales Murillo, David Eduardo Pinto Avendaño, Franco Rojas López
• Recommendation System Rest-Mex 2022 for Mexican Tourism Using Natural Language Processing
  Santiago Veigas Ramírez, Daniel Martínez Davies, Isabel Segura Bedmar
• A Transfer Learning Model for Polarity in Touristic Reviews in Spanish from TripAdvisor
  Daniel Mendoza, Jorge Ramos−Zavaleta, Adrian Rodríguez
• AutoML and Ensemble Transformers for Sentiment Analysis in Mexican Tourism Texts
  Victor Gómez−Espinos, Victor Muñiz−Sanchez, Adrián Pastor López−Monroy
• BERT and Data Augmentation for Sentiment Analysis in TripAdvisor Reviews
  Enrique Santibáñez−Cortés, Azael Carrillo−Cabrera, Yair Antonio Castillo−Castillo, Daniela Alejandra Moctezuma−Ochoa, Victor Hugo Muñiz−Sánchez
• Sentiment Analysis in Spanish Reviews: Dataket Submission on REST-Mex 2022
  Gabriel Missael Barco, Gil Estéfano Rodríguez Rivera, Delia Irazú Hernández Farías
• Opinion Mining of the Mexican Tourism Sector through Sets of Normalized N-Grams
  Juan Carlos Rivas−Álvarez, René Arnulfo García−Hernández, Sergio Iván Medina−Martínez, Ana Mercedes Martínez−Ortiz, Néstor Hernández−Castañeda, José Esteban Ruiz−Melo, Ángel Hernández−Castañeda, Yulia Nikolaevna−Ledeneva
• Participation of ESCOM's Data Science Group at Rest-Mex 2022: Sentiment Analysis Task
  Julian Alcibar−Zubillaga, Yanina De−Luna Ocampo, Isaias Pacheco−Castillo, Kevin Ramirez−Mendez, Juan−Pablo−Minoru Sainz−Takata, Omar Juárez Gambino
• The Role of the Topics for the Sentiment Analysis Task on a Mexican Tourist Collection
  Juan David Jurado−Buch, Lázaro Bustio−Martínez, Miguel Ángel Álvarez−Carmona
• Transformers Approach for Sentiment Analysis: Classification of Mexican Tourists Reviews from TripAdvisor
  Mario Pérez Enríquez, Javier Alonso Mencía, Isabel Segura−Bedmar
• Fine-tuning mT5-based Transformer via CMA-ES for Sentiment Analysis
  Orlando Grabiel Toledano−López, Julio Madera, Hector González, Alfredo Simón−Cuevas, Thomas Demeester, Erik Mannens
• UMUTeam at REST-MEX 2022: Polarity Prediction using Knowledge Integration of Linguistic Features and Sentence Embeddings based on Transformers
  José Antonio García−Díaz, Miguel Ángel Rodríguez−García, Francisco García−Sánchez, Rafael Valencia−García
• A Proposal and Comparison of Supervised and Unsupervised Classification Techniques for Sentiment Analysis in Tourism Data
  Antonio Rico−Sulayes, Julian Monsalve−Pulido
• A Mexico's Covid Traffic Light Color Prediction System Based on Mexican News
  Jorge Ramos−Zavaleta, Adrian Rodríguez
• Combining Linear Regressions to Determine the Future of the Covid in Mexico from the News
  Gabriela Carmona−Sánchez, Ángel Carmona, Miguel Ángel Álvarez−Carmona
• Mexican Epidemiological Semaphore Color Prediction by Means of Mutual Information Features
  Alejandra Romero−Cantón, Ramon Aranda, Angel Diaz−Pacheco, Juan Pablo Ramírez−Silva

Detection of Aggressive and Violent INCIdents from Social Media in Spanish (DA-VINCIS@IberLEF2022)

• Multi-Task Learning for Detection of Aggressive and Violent Incidents from Social Media
  Hoang Thang Ta, Abu Bakar Siddiqur Rahman, Lotfollah Najjar, Alexander Gelbukh
• Detection of Aggressive and Violent Incidents from Social Media in Spanish using Pre-trained Language Model
  Atnafu Lambebo Tonja, Muhammad Arif, Olga Kolesnikova, Alexander Gelbukh, Grigori Sidorov,
• Leveraging Events Sub-Categories for Violent-Events Detection in Social Media
  Daniel Vallejo−Aldana, Adrián Pastor López−Monroy, Esaú Villatoro−Tello
• Vicomtech at DA-VINCIS: Detection of Aggressive and Violent Incidents from Social Media in Spanish
  Pablo Turón, Naiara Perez, Aitor García−Pablos, Elena Zotova, Montse Cuadros
• ITAINNOVA@DA-VINCIS: A Tale of Transformers and Simple Optimization Techniques
  Rosa María Montañés−Salas, Rafael del−Hoyo−Alonso, Paula Peña−Larena
• Prompt Based Framework for Violent Event Recognition in Spanish
  Guanqiu Qin, Junheng He, Qifeng Bai, Nankai Lin, Jigang Wang, Kang Zhou, Dong Zhou, Aimin Yang
• GAN-BERT: Adversarial Learning for Detection of Aggressive and Violent Incidents from Social Media
  Hoang Thang Ta, Abu Bakar Siddiqur Rahman, Lotfollah Najjar, Alexander Gelbukh
• UMUTeam at DA-VINCIS 2022: Aggressive and Violent Classification using Knowledge Integration and Ensemble Learning
  José Antonio García−Díaz, Salud María Jiménez−Zafra, Miguel Ángel Rodríguez−García, Rafael Valencia−García

DETEction and classification of racial STereotypes in Spanish (DETESTS 2022)

• UMUTeam at IberLEF-2022 DETESTS task: Feature Engineering for the Identification and Categorization of Racial Stereotypes in Spanish
  José Antonio García−Díaz, Salud María Jiménez−Zafra, Rafael Valencia−García
• MALNIS at IberLEF-2022 DETESTS Task: A Multi-Task Learning Approach for Low-Resource Detection of Racial Stereotypes in Spanish
  Juan Ramirez−Orta, María Virginia Sabando, Mariano Maisonnave, Evangelos Milios
• I2C at IberLEF-2022 DETESTS task: Detection of Racist Stereotypes in Spanish Comments using UnderBagging and Transformers
  Jacinto Mata Vázquez, Victoria Pachón Álvarez, Chaimae Tayebi Taybi, Pablo Pizarro Sánchez
• Lak_NLP at IberLEF-2022 DETESTS task: Automatic Classification of Stereotypes in Text
  Fatima Laknani, Mercedes García Martinez
• DaMinCi at IberLEF-2022 DETESTS task: Detection and Classification of Racial Stereotypes in Spanish
  David Cabestany, Clara Adsuar, Miguel López

sEXism Identification in Social neTworks (EXIST 2022)

• Transfer Learning for Automatic Sexism Detection with Multilingual Transformer Models - AIT_FHSTP@EXIST2022
  Daria Liakhovets, Mina Schütz, Jaqueline Böck, Medina Andresel, Armin Kirchknopf, Andreas Babic, Djordje Slijepčević, Jasmin Lampert, Alexander Schindler, Matthias Zeppelzauer
• Detection and Classification of Sexism on Social Media Using Multiple Languages, Transformers, and Ensemble Models
  Angel Felipe Magnossão de Paula, Roberto Fray da Silva
• Detecting and Classifying Sexism by Ensembling Transformers Models
  Alejandro Vaca−Serrano
• Bi-Ensembles of Transformer for Online Bilingual Sexism Detection
  Emilio Villa−Cueva, Fernando Sanchez−Vega, Adrián Pastor López−Monroy
• Enhancing Sexism Identification and Categorization in Low-data Situations
  Vicent Ahuir, José Ángel González, Lluís−Felip Hurtado
• Automatic Sexism Identification Using an Ensemble of Pretrained Transformers
  Victoria Pachón Álvarez, Jacinto Mata Vázquez, Wissam Chibane, Juan Luis Domínguez Olmedo
• Are Examples Worth More Than Language?
  Roberto Labadie Tamayo, Reynier Ortega Bueno
• Multiaztertest@Exist-Iberlef2022: Sexism Identification in Social Networks
  Kepa Bengoetxea, Amaia Aguirregoitia
• NIT-Agartala-NLP-Team at EXIST 2022: Sexism Identification in Social Networks
  Amaan Rizvi, Anupam Jamatia
• Sexism Identification In Social Media Using Deep Learning Models
  Gersome Shimi, Jerin Mahibha, Durairaj Thenmozhi
• SINAI at EXIST 2022: Exploring Data Augmentation and Machine Translation for Sexism Identification
  Daniel García−Baena, Miguel Ángel García−Cumbreras, Salud María Jiménez−Zafra, Manuel García-Vega
• Exploring the Use of Different Linguistic Phenomena for Sexism Identification in Social Networks
  Flor Miriam Plaza−del−Arco, María−Dolores Molina−González, Luis Alfonso Ureña−López, María−Teresa Martín−Valdivia
• Transfer Learning from Multilingual DeBERTa for Sexism Identification
  Hoang Thang Ta, Abu Bakar Siddiqur Rahman, Lotfollah Najjar, Alexander Gelbukh
• UMUTeam at EXIST 2022: Knowledge Integration and Ensemble Learning for Multilingual Sexism Identification and Categorization using Linguistic Features and Transformers
  José Antonio García−Díaz, Salud María Jiménez−Zafra, Ricardo Colomo−Palacios, Rafael Valencia−García
• A Framework for Sexism Detection on Social Media via ByT5 and TabNet
  Arjumand Younus, Muhammad Atif Qureshi

Named-Entity Recognition and entity linking for living being mentions (LivingNER)

• Vicomtech at LivingNER2022
  Elena Zotova, Aitor García−Pablos, Naiara Perez, Pablo Turón, Montse Cuadros
• Species Entity Recognition Using a Neural Inhibitory Mechanism
  Andrei−Marius Avram, Maria Mitrofan, Vasile Păis
• The READ-BioMed Team in LivingNER Task 1 (2022): Adaptation of an English Annotation System to Spanish
  Antonio Jimeno Yepes, Karin Verspoor
• SINAI at LivingNER Shared Task 2022: Species Mention Recognition and Normalization Using Transfer Learning and String Matching Techniques
  Mariia Chizhikova, Jaime Collado−Montañez, Pilar López−Úbeda, Manuel Carlos Díaz−Galiano, Luis Alfonso Ureña−López, María Teresa Martín−Valdivia
• FLERT-Matcher: A Two-Step Approach for Clinical Named Entity Recognition and Normalization
  Matías Rojas, Jose Barros, Mauricio Araneda, Jocelyn Dunstan
• Task-Aware Contrastive Pre-training for Spanish Named Entity Recognition in LivingNER Challenge
  Sumam Francis, Marie−Francine Moens
• Multi-Input RIM for Named-Entity Recognition in Spanish Clinical Reports
  Parsa Bagherzadeh, Harsh Verma, Sabine Bergler
• Biomedical Named Entity Recognition in Eight Languages with Zero Code Changes
  Veysel Kocaman, Gursev Pirge, Bunyamin Polat, David Talby
• Named Entity Recognition For Humans and Species With Domain-Specific and Domain-Adapted Transformer Models
  Alejandro Vaca−Serrano
• Species Mention Entity Recognition, Linking and Classification Using RoBERTa in Combination with Spanish Medical Embeddings
  Rodrigo del Moral, Javier Reyes−Aguillón, Orlando Ramos−Flores, Helena Gómez−Adorno, Gemma Bel−Enguix
• IAM at IberLEF 2022: NER of Species Mentions
  Sébastien Cossin, Gayo Diallo, Vianney Jouhet
• Multilingual Medical Entity Recognition and Cross-lingual Zero-Shot Linking with Facebook AI Similarity Search
  Marcel Schwarz, Kathryn Chapman, Bertram Häussler
• ParTNER: Paragraph Tuning for Named Entity Recognition on Clinical Cases in Spanish using mBERT + Rules
  Antonio Tamayo, Diego Burgos, Alexander Gelbukh
• BERT-BiLSTM Model for Entity Recognition in Clinical Text
  Zhengzhong Zhu, Liqing Wang
• Clinical Text Entity Recognition Based on Pretrained Model and BiGRU-CRF
  Hanjie Mai, Xiaobing Zhou
• Named Entity Recognition for LivingNER-Species based on BERT and Span Detection
  Song Han, Haiyan Ding

Paraphrase Identification in Mexican Spanish (PAR-MEX)

• Paraphrase Identification: Lightweight Effective Methods Based Features from Pre-trained Models
  Abu Bakar Siddiqur Rahman, Hoang Thang Ta, Lotfollah Najjar, Alexander Gelbukh
• UC3M at PAR-MEX@IberLef 2022: From Cosine Distance to Transformer Models for Paraphrase Identification in Mexican Spanish
  Angela Brando−Le−Bihan, Roman Karbushev, Isabel Segura−Bedmar
• PAR-MEX Shared Task Submission Description:Identifying Spanish Paraphrases Using Pretrained Models and Translations
  Leander Girrbach
• GAN-BERT, an Adversarial Learning Architecture for Paraphrase Identification
  Hoang Thang Ta, Abu Bakar Siddiqur Rahman, Lotfollah Najjar, Alexander Gelbukh
• Mexican Spanish Paraphrase Identification using Data Augmentation
  Abdul Meque, Fazlourrahman Balouchzahi, Grigori Sidorov, Alexander Gelbukh
• Using Transformers on Noisy vs. Clean Data for Paraphrase Identification in Mexican Spanish
  Antonio Tamayo, Diego A. Burgos, Alexander Gelbukh

Question Answering Learning from Examples in Spanish (QuALES)

• UNED at QuALES 2022: Testing the Performance of Transformer-Based Language Models for Spanish Question-Answering
  Alvaro Rodrigo, Anselmo Peñas
• Supervised Domain Adaptation for Extractive Question Answering in Spanish
  Santiago Máximo
• Adversarial Question Answering in Spanish with Transformer Models
  Alejandro Vaca−Serrano

Reading Comprehension and Reasoning Explanation for Spanish (ReCoRES)

• Study on Text Comprehension and MCQA in Spanish
  Pablo Baggetto, Sofía Ramos, Joan García, José Ramón Navarro
• Zero-shot Reading Comprehension and Reasoning for Spanish with BERTIN GPT-J-6B
  Javier De la Rosa, Andrés Fernández