arXiv 2508.086502025-08-12cs.CL

UWB at WASSA-2024 Shared Task 2: 跨语言情感检测

UWB at WASSA-2024 Shared Task 2: Cross-lingual Emotion Detection

University of West Bohemia, Faculty of Applied Sciences（西波西米亚大学应用科学学院）；Department of Computer Science and Engineering（计算机科学与工程系）；NTIS – New Technologies for the Information Society（信息社会新技术机构）

Jakub Šmíd, Pavel Přibáň, Pavel Král

备注：: Published in Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis (WASSA 2024). Official version: https://aclanthology.org/2024.wassa-1.47/
DOI：: 10.18653/v1/2024.wassa-1.47

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文针对WASSA-2024跨语言情感检测任务，提出基于微调量化大模型与多语言Transformer的方法，结合机器翻译与触发词切换技术，在触发词与情感检测子任务中取得前三名优异成绩。

摘要：

本文介绍了我们为WASSA-2024跨语言情感检测共享任务构建的系统。该任务包含两个子任务：首先，为五种语言之一的给定推文从六个可能的类别中评估情感标签；其次，以二进制和数值格式预测触发所检测情感的词语。我们提出的方法围绕微调量化大型语言模型（特别是Orca~2，结合低秩适配器LoRA）以及多语言Transformer模型（如XLM-R和mT5）展开。我们通过机器翻译增强两个子任务的性能，并在第二个子任务中采用触发词切换技术。该系统取得了优异性能，在数值触发词检测中排名第1，在二进制触发词检测中排名第3，在情感检测中排名第7。

英文摘要：

This paper presents our system built for the WASSA-2024 Cross-lingual Emotion Detection Shared Task. The task consists of two subtasks: first, to assess an emotion label from six possible classes for a given tweet in one of five languages, and second, to predict words triggering the detected emotions in binary and numerical formats. Our proposed approach revolves around fine-tuning quantized large language models, specifically Orca~2, with low-rank adapters (LoRA) and multilingual Transformer-based models, such as XLM-R and mT5. We enhance performance through machine translation for both subtasks and trigger word switching for the second subtask. The system achieves excellent performance, ranking 1st in numerical trigger words detection, 3rd in binary trigger words detection, and 7th in emotion detection.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。