不用分词的模型在讽刺检测上表现更好，尤其适合社交媒体文本。
Token-free Models for Sarcasm Detection
- 直接处理原始字符或字节，避免分词带来的词汇不匹配问题。
- ByT5-small和CANINE在新闻标题和推特数据集上分别提升0.77%和0.49%准确率。
- 适合处理嘈杂、非正式的社交文本，是鲁棒NLP的新方向。
分词是大多数自然语言处理流程的基础步骤，但常引发词汇不匹配和未登录词问题。近期研究表明，直接在字节或字符层面操作的模型可缓解这些局限。本文评估了两种无分词模型——ByT5和CANINE——在社交媒体（推特）与非社交媒体（新闻标题）领域中的讽刺检测表现。通过微调并对比基于分词的基线模型及当前最优方法，结果表明：ByT5-small和CANINE均优于传统分词模型，在新闻标题和推特讽刺检测数据集上分别实现0.77%和0.49%的准确率提升，达到新最佳性能。这些发现凸显了无分词模型在噪声大、非正式场景下的潜力。
原文摘要 · Abstract (English)
Tokenization is a foundational step in most natural language processing (NLP) pipelines, yet it introduces challenges such as vocabulary mismatch and out-of-vocabulary issues. Recent work has shown that models operating directly on raw text at the byte or character level can mitigate these limitations. In this paper, we evaluate two token-free models, ByT5 and CANINE, on the task of sarcasm detection in both social media (Twitter) and non-social media (news headlines) domains. We fine-tune and benchmark these models against token-based baselines and state-of-the-art approaches. Our results show that ByT5-small and CANINE outperform token-based counterparts and achieve new state-of-the-art performance, improving accuracy by 0.77% and 0.49% on the News Headlines and Twitter Sarcasm datasets, respectively. These findings underscore the potential of token-free models for robust NLP in noisy and informal domains such as social media.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。