arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.23280cs.CL
收藏

电商直播场景中的中文形态解析

Chinese Morph Resolution in E-commerce Live Streaming Scenarios

School of Information Engineering, Yangzhou University, China(扬州大学信息工程学院);China Academy of Electronic and Information Technology, China(中国电子信息技术研究院)

Jiahao Zhu, Jipeng Qiang, Ran Bai, Chenyu Liu, Xiaoye Ouyang

AI总结:

本研究提出LiveAMR任务,通过形态解析技术提升电商直播中的虚假宣传检测能力。

摘要:

中国电商直播,特别是像抖音这样的平台,已成为主要的销售渠道,但主播常使用形态来逃避审查并进行虚假宣传。本研究引入了Live Auditory Morph Resolution(LiveAMR)任务来检测此类违规行为。与以往专注于社交媒体和地下行业文本-based逃避的研究不同,LiveAMR针对健康和医疗直播中的语音-based逃避。我们构建了第一个LiveAMR数据集,包含86,790个样本,并开发了一种将任务转化为文本到文本生成问题的方法。通过利用大型语言模型(LLMs)生成额外的训练数据,我们提高了性能,并证明形态解析显著增强了直播监管。

英文摘要:

E-commerce live streaming in China, particularly on platforms like Douyin, has become a major sales channel, but hosts often use morphs to evade scrutiny and engage in false advertising. This study introduces the Live Auditory Morph Resolution (LiveAMR) task to detect such violations. Unlike previous morph research focused on text-based evasion in social media and underground industries, LiveAMR targets pronunciation-based evasion in health and medical live streams. We constructed the first LiveAMR dataset with 86,790 samples and developed a method to transform the task into a text-to-text generation problem. By leveraging large language models (LLMs) to generate additional training data, we improved performance and demonstrated that morph resolution significantly enhances live streaming regulation.

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。

↑