YEZE at SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization via Heterogeneous Ensembling

• URL: http://arxiv.org/abs/2605.06231v2
• Date: Fri, 08 May 2026 21:45:50 GMT
• Title: YEZE at SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization via Heterogeneous Ensembling
• Abstract summary: We propose a heterogeneous ensemble of multilingual pretrained models, combining XLM-RoBERTa-large and mDeBERTa-v3-base.<n>We investigate techniques such as multi-task learning, translation-based data augmentation, and class weighting to improve classification performance under severe label imbalance.
• Score: 3.3438708071539445
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents our system for SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization, which identifies polarized social media content in 22 languages through three subtasks: binary detection, target classification, and manifestation identification. We propose a heterogeneous ensemble of multilingual pretrained models, combining XLM-RoBERTa-large and mDeBERTa-v3-base. We investigate techniques such as multi-task learning, translation-based data augmentation, and class weighting to improve classification performance under severe label imbalance. Our findings indicate that independent task modeling combined with class weighting is more effective.

Related papers

• mdok-style at SemEval-2026 Task 9: Finetuning LLMs for Multilingual Polarization Detection [5.3677118215189585]
  SemEval-2026 Task 9 is focused on multilingual polarization detection.<n>It covers the identification of multilingual, multicultural and multievent polarization along three axes, namely detection, type, and manifestation.<n>We have coped with this SemEval task by finetuning mid-size LLMs for the sequence-classification task using the QLoRA parameter-efficient finetuning technique.<n>The training data augmented the multilingual (22 languages) training sets by anonymized, lower-cased, upper-cased, and homoglyphied counterparts, making the detection more robust.
  arXiv  Detail & Related papers  (2026-05-04T15:08:24Z)
• SemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures [93.36078244548077]
  The task data consist of an extended version of our manually constructed BLEnD benchmark (Myung et al. 2024), covering more than 30 language-culture pairs.<n>As the task is designed strictly for evaluation, participants were not permitted to use the data for training, fine-tuning, few-shot learning, or any other form of model modification.<n>We report the results and present an analysis of the best-performing systems and the most commonly adopted approaches.
  arXiv  Detail & Related papers  (2026-05-04T13:49:44Z)
• SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization [47.011443052131376]
  We present SemEval-2026 Task 9, a shared task on online polarization detection, covering 22 languages and comprising over 110K annotated instances.<n>Participants were asked to predict labels in three sub-tasks: (1) detecting the presence of polarization, (2) identifying the type of polarization, and (3) recognizing the polarization manifestation.<n>We report the baseline results and analyze the performance of the best-performing systems, highlighting the most common approaches and the most effective methods across different subtasks and languages.
  arXiv  Detail & Related papers  (2026-04-08T08:34:55Z)
• SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection [76.18321723846616]
  Task covers more than 30 languages from seven distinct language families.<n>Data instances are multi-labeled with six emotional classes, with additional datasets in 11 languages annotated for emotion intensity.<n>Participants were asked to predict labels in three tracks: (a) multilabel emotion detection, (b) emotion intensity score detection, and (c) cross-lingual emotion detection.
  arXiv  Detail & Related papers  (2025-03-10T12:49:31Z)
• KInITVeraAI at SemEval-2023 Task 3: Simple yet Powerful Multilingual Fine-Tuning for Persuasion Techniques Detection [0.0]
  This paper presents the best-performing solution to the SemEval 2023 Task 3 on the subtask 3 dedicated to persuasion techniques detection. Due to a high multilingual character of the input data and a large number of 23 predicted labels, we opted for fine-tuning pre-trained transformer-based language models.
  arXiv  Detail & Related papers  (2023-04-24T09:06:43Z)
• Hitachi at SemEval-2023 Task 3: Exploring Cross-lingual Multi-task Strategies for Genre and Framing Detection in Online News [10.435874177179764]
  This paper explains the participation of team Hitachi to SemEval-2023 Task 3 "Detecting the genre, the framing, and the persuasion techniques in online news in a multi-lingual setup" We investigated different cross-lingual and multi-task strategies for training the pretrained language models. We constructed ensemble models from the results and achieved the highest macro-averaged F1 scores in Italian and Russian genre categorization subtasks.
  arXiv  Detail & Related papers  (2023-03-03T09:12:55Z)
• 1Cademy at Semeval-2022 Task 1: Investigating the Effectiveness of Multilingual, Multitask, and Language-Agnostic Tricks for the Reverse Dictionary Task [13.480318097164389]
  We focus on the Reverse Dictionary Track of the SemEval2022 task of matching dictionary glosses to word embeddings. Models convert the input of sentences to three types of embeddings: SGNS, Char, and Electra. Our proposed Elmobased monolingual model achieves the highest outcome.
  arXiv  Detail & Related papers  (2022-06-08T06:39:04Z)
• xGQA: Cross-Lingual Visual Question Answering [100.35229218735938]
  xGQA is a new multilingual evaluation benchmark for the visual question answering task. We extend the established English GQA dataset to 7 typologically diverse languages. We propose new adapter-based approaches to adapt multimodal transformer-based models to become multilingual.
  arXiv  Detail & Related papers  (2021-09-13T15:58:21Z)
• Are Multilingual Models Effective in Code-Switching? [57.78477547424949]
  We study the effectiveness of multilingual language models to understand their capability and adaptability to the mixed-language setting. Our findings suggest that pre-trained multilingual models do not necessarily guarantee high-quality representations on code-switching.
  arXiv  Detail & Related papers  (2021-03-24T16:20:02Z)
• Explicit Alignment Objectives for Multilingual Bidirectional Encoders [111.65322283420805]
  We present a new method for learning multilingual encoders, AMBER (Aligned Multilingual Bi-directional EncodeR) AMBER is trained on additional parallel data using two explicit alignment objectives that align the multilingual representations at different granularities. Experimental results show that AMBER obtains gains of up to 1.1 average F1 score on sequence tagging and up to 27.3 average accuracy on retrieval over the XLMR-large model.
  arXiv  Detail & Related papers  (2020-10-15T18:34:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.