← Back to papers
2023 ACL ACL 2023

HHU at SemEval-2023 Task 3: An Adapter-based Approach for News Genre Classification

Abstract

AbstractThis paper describes our approach for Subtask 1 of Task 3 at SemEval-2023. In this subtask, task participants were asked to classify multilingual news articles for one of three classes: Reporting, Opinion Piece or Satire. By training an AdapterFusion layer composing the task-adapters from different languages, we successfully combine the language-exclusive knowledge and show that this improves the results in nearly all cases, including in zero-shot scenarios.

🌉 Interdisciplinary Bridge — Artificial Intelligence and Machine Learning
🧭 Keyword Pioneer — news genre classification
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Fabian Billert , Stefan Conrad

Topics

Artificial Intelligence > Learning Paradigms > Transfer Learning Machine Learning > Core Methods > Classification Artificial Intelligence > Learning Paradigms > Zero-Shot Learning

Keywords

zero-shot learning transfer learning text classification multilingual model adapter fusion news genre classification
Download PDF

Related papers

Helping a Friend or Supporting a Cause? Disentangling Active and Passive Cosponsorship in the U.S. Congress 2023
History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling 2023
Efficient Transformers with Dynamic Token Pooling 2023
NAP at SemEval-2023 Task 3: Is Less Really More? (Back-)Translation as Data Augmentation Strategies for Detecting Persuasion Techniques 2023
SUT at SemEval-2023 Task 1: Prompt Generation for Visual Word Sense Disambiguation 2023