Uddessho：面向低资源孟加拉语多模态作者意图分类的大规模基准数据集
Uddessho: An Extensive Benchmark Dataset for Multimodal Author Intent Classification in Low-Resource Bangla Language
AI总结：
针对低资源孟加拉语社交媒体帖子的作者意图分类难题，该研究提出多模态MABIC框架，构建含3048个样本的Uddessho基准数据集，多模态方法准确率达76.19%，较单模态提升11.66%，为该领域首项研究。
摘要：
随着互联网上日常信息共享与获取的日益普及，本文提出了一种孟加拉语意图分类的创新方法，聚焦于人们分享想法与观点的社交媒体帖子场景。该方法利用多模态数据，重点关注作者身份识别，旨在理解文本内容背后的潜在目的，尤其是在社交媒体上各类用户生成帖子的语境下。当前方法在孟加拉语这类低资源语言中常面临挑战，尤其是当作者特征与意图紧密关联时——正如社交媒体帖子中所呈现的那样。为解决这一问题，我们提出了基于多模态的孟加拉语作者意图分类（Multimodal-based Author Bangla Intent Classification，MABIC）框架，利用文本与图像更深入地洞察所传达的意图。我们构建了名为“Uddessho”的数据集，包含来自社交媒体的3048个样本。我们的方法包含两种分类路径，分别用于文本意图分类与多模态作者意图分类，融合了早期融合与晚期融合技术。实验中，单模态方法在孟加拉语文本意图识别任务上的准确率为64.53%。相比之下，我们的多模态方法显著优于传统单模态方法，准确率达到76.19%，提升了11.66%。据我们所知，这是首个针对低资源孟加拉语社交媒体帖子的多模态作者意图分类研究工作。
英文摘要：
With the increasing popularity of daily information sharing and acquisition on the Internet, this paper introduces an innovative approach for intent classification in Bangla language, focusing on social media posts where individuals share their thoughts and opinions. The proposed method leverages multimodal data with particular emphasis on authorship identification, aiming to understand the underlying purpose behind textual content, especially in the context of varied user-generated posts on social media. Current methods often face challenges in low-resource languages like Bangla, particularly when author traits intricately link with intent, as observed in social media posts. To address this, we present the Multimodal-based Author Bangla Intent Classification (MABIC) framework, utilizing text and images to gain deeper insights into the conveyed intentions. We have created a dataset named "Uddessho," comprising 3,048 instances sourced from social media. Our methodology comprises two approaches for classifying textual intent and multimodal author intent, incorporating early fusion and late fusion techniques. In our experiments, the unimodal approach achieved an accuracy of 64.53% in interpreting Bangla textual intent. In contrast, our multimodal approach significantly outperformed traditional unimodal methods, achieving an accuracy of 76.19%. This represents an improvement of 11.66%. To our best knowledge, this is the first research work on multimodal-based author intent classification for low-resource Bangla language social media posts.
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。
