当前位置: X-MOL 学术arXiv.cs.CL › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
WESSA at SemEval-2020 Task 9: Code-Mixed Sentiment Analysis using Transformers
arXiv - CS - Computation and Language Pub Date : 2020-09-21 , DOI: arxiv-2009.09879
Ahmed Sultan (WideBot), Mahmoud Salim (WideBot), Amina Gaber (WideBot), Islam El Hosary (WideBot)

In this paper, we describe our system submitted for SemEval 2020 Task 9, Sentiment Analysis for Code-Mixed Social Media Text alongside other experiments. Our best performing system is a Transfer Learning-based model that fine-tunes "XLM-RoBERTa", a transformer-based multilingual masked language model, on monolingual English and Spanish data and Spanish-English code-mixed data. Our system outperforms the official task baseline by achieving a 70.1% average F1-Score on the official leaderboard using the test set. For later submissions, our system manages to achieve a 75.9% average F1-Score on the test set using CodaLab username "ahmed0sultan".

中文翻译:

SemEval-2020 中的 WESSA 任务 9:使用 Transformer 进行代码混合情绪分析

在本文中,我们描述了我们提交给 SemEval 2020 任务 9,代码混合社交媒体文本的情感分析以及其他实验的系统。我们表现​​最好的系统是一个基于迁移学习的模型,它可以在单语英语和西班牙语数据以及西班牙语-英语代码混合数据上微调“XLM-RoBERTa”,这是一种基于转换器的多语言掩码语言模型。我们的系统使用测试集在官方排行榜上实现了 70.1% 的平均 F1-Score,优于官方任务基线。对于以后的提交,我们的系统设法使用 CodaLab 用户名“ahmed0sultan”在测试集上实现了 75.9% 的平均 F1-Score。
更新日期:2020-09-22
down
wechat
bug