GateNLP at SemEval-2025 Task 10: Hierarchical Three-Step Prompting for Multilingual Narrative Classification

• URL: http://arxiv.org/abs/2505.22867v1
• Date: Wed, 28 May 2025 20:59:28 GMT
• Title: GateNLP at SemEval-2025 Task 10: Hierarchical Three-Step Prompting for Multilingual Narrative Classification
• Authors: Iknoor Singh, Carolina Scarton, Kalina Bontcheva,
• Abstract summary: This paper presents our approach to SemEval 2025 Task 10 Subtask 2.<n>It aims to classify news articles into a pre-defined two-level taxonomy of main narratives and sub-narratives across multiple languages.<n>Our methodology follows a three-step Large Language Model (LLM) prompting strategy.
• Score: 6.315106341032209
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The proliferation of online news and the increasing spread of misinformation necessitate robust methods for automatic data analysis. Narrative classification is emerging as a important task, since identifying what is being said online is critical for fact-checkers, policy markers and other professionals working on information studies. This paper presents our approach to SemEval 2025 Task 10 Subtask 2, which aims to classify news articles into a pre-defined two-level taxonomy of main narratives and sub-narratives across multiple languages. We propose Hierarchical Three-Step Prompting (H3Prompt) for multilingual narrative classification. Our methodology follows a three-step Large Language Model (LLM) prompting strategy, where the model first categorises an article into one of two domains (Ukraine-Russia War or Climate Change), then identifies the most relevant main narratives, and finally assigns sub-narratives. Our approach secured the top position on the English test set among 28 competing teams worldwide. The code is available at https://github.com/GateNLP/H3Prompt.

Related papers

• Understanding Cross-Lingual Alignment -- A Survey [52.572071017877704]
  Cross-lingual alignment is the meaningful similarity of representations across languages in multilingual language models. We survey the literature of techniques to improve cross-lingual alignment, providing a taxonomy of methods and summarising insights from throughout the field.
  arXiv  Detail & Related papers  (2024-04-09T11:39:53Z)
• SheffieldVeraAI at SemEval-2023 Task 3: Mono and multilingual approaches for news genre, topic and persuasion technique classification [3.503844033591702]
  This paper describes our approach for SemEval-2023 Task 3: Detecting the category, the framing, and the persuasion techniques in online news in a multi-lingual setup.
  arXiv  Detail & Related papers  (2023-03-16T15:54:23Z)
• Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue [92.01165203498299]
  Embodied dialogue instruction following requires an agent to complete a complex sequence of tasks from a natural language exchange. This paper argues that imitation learning (IL) and related low-level metrics are actually misleading and do not align with the goals of embodied dialogue research.
  arXiv  Detail & Related papers  (2022-10-10T05:51:40Z)
• Distant finetuning with discourse relations for stance classification [55.131676584455306]
  We propose a new method to extract data with silver labels from raw text to finetune a model for stance classification. We also propose a 3-stage training framework where the noisy level in the data used for finetuning decreases over different stages. Our approach ranks 1st among 26 competing teams in the stance classification track of the NLPCC 2021 shared task Argumentative Text Understanding for AI Debater.
  arXiv  Detail & Related papers  (2022-04-27T04:24:35Z)
• Galileo at SemEval-2020 Task 12: Multi-lingual Learning for Offensive Language Identification using Pre-trained Language Models [11.868582973877626]
  This paper describes Galileo's performance in SemEval-2020 Task 12 on detecting and categorizing offensive language in social media. For Offensive Language Identification, we proposed a multi-lingual method using Pre-trained Language Models, ERNIE and XLM-R. For offensive language categorization, we proposed a knowledge distillation method trained on soft labels generated by several supervised models.
  arXiv  Detail & Related papers  (2020-10-07T17:40:19Z)
• Cross-lingual Extended Named Entity Classification of Wikipedia Articles [0.0]
  This paper describes our method to solving the problem and discusses the official results. We propose a three-stage approach including multilingual model pre-training, monolingual model fine-tuning and cross-lingual voting. Our system is able to achieve the best scores for 25 out of 30 languages; and its accuracy gaps to the best performing systems of the other five languages are relatively small.
  arXiv  Detail & Related papers  (2020-10-07T14:06:09Z)
• Detecting and Classifying Malevolent Dialogue Responses: Taxonomy, Data and Methodology [68.8836704199096]
  Corpus-based conversational interfaces are able to generate more diverse and natural responses than template-based or retrieval-based agents. With their increased generative capacity of corpusbased conversational agents comes the need to classify and filter out malevolent responses. Previous studies on the topic of recognizing and classifying inappropriate content are mostly focused on a certain category of malevolence.
  arXiv  Detail & Related papers  (2020-08-21T22:43:27Z)
• LTIatCMU at SemEval-2020 Task 11: Incorporating Multi-Level Features for Multi-Granular Propaganda Span Identification [70.1903083747775]
  This paper describes our submission for the task of Propaganda Span Identification in news articles. We introduce a BERT-BiLSTM based span-level propaganda classification model that identifies which token spans within the sentence are indicative of propaganda.
  arXiv  Detail & Related papers  (2020-08-11T16:14:47Z)
• Pre-training via Paraphrasing [96.79972492585112]
  We introduce MARGE, a pre-trained sequence-to-sequence model learned with an unsupervised multi-lingual paraphrasing objective. We show it is possible to jointly learn to do retrieval and reconstruction, given only a random initialization. For example, with no additional task-specific training we achieve BLEU scores of up to 35.8 for document translation.
  arXiv  Detail & Related papers  (2020-06-26T14:43:43Z)
• BPGC at SemEval-2020 Task 11: Propaganda Detection in News Articles with Multi-Granularity Knowledge Sharing and Linguistic Features based Ensemble Learning [2.8913142991383114]
  SemEval 2020 Task-11 aims to design automated systems for news propaganda detection. Task-11 consists of two sub-tasks, namely, Span Identification and Technique Classification.
  arXiv  Detail & Related papers  (2020-05-31T19:35:53Z)

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.