SentiCSE：一种具有情感引导文本相似度的情感感知对比句嵌入框架
SentiCSE: A Sentiment-aware Contrastive Sentence Embedding Framework with Sentiment-guided Textual Similarity
AI总结：
本文针对情感感知预训练语言模型忽视表示质量评估的问题，提出情感引导文本相似度指标SgTS和情感感知对比句嵌入框架SentiCSE，通过词级与句子级联合目标构建高质量情感表示，并在定性与定量比较中展现出优越性。
摘要：
近年来，情感感知的预训练语言模型（PLMs）在下游情感分析任务中表现出令人印象深刻的结果。然而，它们忽视了对所构建情感表示质量的评估；它们只专注于提高微调性能，这掩盖了表示质量的重要性。我们认为，在不保证表示质量的情况下，它们的下游性能可能高度依赖于微调数据的监督，而不是表示质量本身。这一问题会使它们难以进入其他情感相关领域，尤其是在标注数据稀缺的情况下。我们首先提出了情感引导文本相似度（SgTS），这是一种用于评估情感表示质量的新指标，其设计基于两个句子之间情感极性等价的程度。然后，我们提出了SentiCSE，一种新颖的情感感知对比句嵌入框架，通过结合词级和句子级目标来构建情感表示，其质量由SgTS保证。与先前的情感感知PLMs进行定性和定量比较，显示了我们的工作的优越性。我们的代码可在以下地址获取：https://github.com/nayohan/SentiCSE
英文摘要：
Recently, sentiment-aware pre-trained language models (PLMs) demonstrate impressive results in downstream sentiment analysis tasks. However, they neglect to evaluate the quality of their constructed sentiment representations; they just focus on improving the fine-tuning performance, which overshadows the representation quality. We argue that without guaranteeing the representation quality, their downstream performance can be highly dependent on the supervision of the fine-tuning data rather than representation quality. This problem would make them difficult to foray into other sentiment-related domains, especially where labeled data is scarce. We first propose Sentiment-guided Textual Similarity (SgTS), a novel metric for evaluating the quality of sentiment representations, which is designed based on the degree of equivalence in sentiment polarity between two sentences. We then propose SentiCSE, a novel Sentiment-aware Contrastive Sentence Embedding framework for constructing sentiment representations via combined word-level and sentence-level objectives, whose quality is guaranteed by SgTS. Qualitative and quantitative comparison with the previous sentiment-aware PLMs shows the superiority of our work. Our code is available at: https://github.com/nayohan/SentiCSE
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。
