arXiv 2304.068452023-05-01cs.CL

SemEval-2023 Task 12：非洲语言情感分析（AfriSenti-SemEval）

SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval)

University of Porto（波尔图大学）；University of Cambridge（剑桥大学）；Universität Hamburg（汉堡大学）；Bahir Dar University（巴赫达尔大学）；National Research Council Canada（加拿大国家研究委员会）；Uppsala University（乌普萨拉大学）；Google Research（谷歌研究院）；Bayero University Kano（贝罗大学卡诺分校）；Ahmadu Bello University, Zaria（扎里亚艾哈迈德·贝罗大学）；University College London（伦敦大学学院）

Shamsuddeen Hassan Muhammad, Idris Abdulmumin, Seid Muhie Yimam, David Ifeoluwa Adelani, Ibrahim Sa'id Ahmad, Nedjma Ousidhoum, Abinew Ayele, Saif M. Mohammad, … 展开作者

Shamsuddeen Hassan Muhammad, Idris Abdulmumin, Seid Muhie Yimam, David Ifeoluwa Adelani, Ibrahim Sa'id Ahmad, Nedjma Ousidhoum, Abinew Ayele, Saif M. Mohammad, Meriem Beloucif, Sebastian Ruder

备注：: 19 pages, 5 figures, 6 tables

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文介绍SemEval-2023的非洲语言情感分析共享任务AfriSenti-SemEval，涵盖14种非洲语言的三类情感分类，设三个子任务并公布各任务最佳成绩与前十系统方法。

摘要：

我们介绍首个以非洲为中心的SemEval共享任务——非洲语言情感分析（AfriSenti-SemEval），数据集可在https://github.com/afrisenti-semeval/afrisent-semeval-2023获取。AfriSenti-SemEval是一项涵盖14种非洲语言的情感分类挑战，语言包括阿姆哈拉语、阿尔及利亚阿拉伯语、豪萨语、伊博语、卢旺达语、摩洛哥阿拉伯语、莫桑比克葡萄牙语、尼日利亚皮钦语、奥罗莫语、斯瓦希里语、提格里尼亚语、契维语、聪加语和约鲁巴语（Muhammad等人，2023），使用标注有3种情感类别的数据。该任务包含三个子任务：（1）任务A：单语分类，收到44份提交；（2）任务B：多语分类，收到32份提交；（3）任务C：零样本分类，收到34份提交。任务A和B的最佳性能由NLNDE团队取得，加权F1值分别为71.31和75.06。UCAS-IIE-NLP在任务C中取得最佳平均分数，加权F1值为58.15。我们还介绍了排名前10的系统所采用的各类方法及其思路。

英文摘要：

We present the first Africentric SemEval Shared task, Sentiment Analysis for African Languages (AfriSenti-SemEval) - The dataset is available at https://github.com/afrisenti-semeval/afrisent-semeval-2023. AfriSenti-SemEval is a sentiment classification challenge in 14 African languages: Amharic, Algerian Arabic, Hausa, Igbo, Kinyarwanda, Moroccan Arabic, Mozambican Portuguese, Nigerian Pidgin, Oromo, Swahili, Tigrinya, Twi, Xitsonga, and Yorùbá (Muhammad et al., 2023), using data labeled with 3 sentiment classes. We present three subtasks: (1) Task A: monolingual classification, which received 44 submissions; (2) Task B: multilingual classification, which received 32 submissions; and (3) Task C: zero-shot classification, which received 34 submissions. The best performance for tasks A and B was achieved by NLNDE team with 71.31 and 75.06 weighted F1, respectively. UCAS-IIE-NLP achieved the best average score for task C with 58.15 weighted F1. We describe the various approaches adopted by the top 10 systems and their approaches.

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。