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 2209.06701cs.CL
收藏

跨语料库Zero-shot情感分类的自然语言推理算法

Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora

Universidad de Jaén(哈恩大学);University of Stuttgart(斯图加特大学)

Flor Miriam Plaza-del-Arco, María-Teresa Martín-Valdivia, Roman Klinger

摘要:

在文本情感分类中,相关标签集取决于领域和应用场景,并且在模型开发时可能不知道。这与监督学习的经典范例相冲突,在经典范例中,标签需要被预定义。获得具有灵活的标签集合的模型的解决方案是使用零样本学习的范例作为自然语言推理任务,这另外增加了不需要任何标记的训练数据的优点。这提出了如何提示用于零样本学习情感分类的自然语言推理模型的问题。提示公式的选项包括情绪名称愤怒或声明“这段文字表达愤怒”。在本文中,我们分析了如何敏感的自然语言推理为基础的zero-shot学习分类器是这样的变化,以提示下考虑的语料库:如何仔细提示需要选择?我们进行实验的一组情感数据集,根据不同的来源(推文,事件,博客)与三个自然语言推理模型呈现不同的语言寄存器,并表明,确实一个特定的提示制定的选择需要适合语料库。我们表明,这一挑战可以解决多种提示的组合。这样的集合在语料库中比单个提示更鲁棒,并且表现出与特定语料库的单个最佳提示几乎相同的性能。

英文摘要:

Within textual emotion classification, the set of relevant labels depends on the domain and application scenario and might not be known at the time of model development. This conflicts with the classical paradigm of supervised learning in which the labels need to be predefined. A solution to obtain a model with a flexible set of labels is to use the paradigm of zero-shot learning as a natural language inference task, which in addition adds the advantage of not needing any labeled training data. This raises the question how to prompt a natural language inference model for zero-shot learning emotion classification. Options for prompt formulations include the emotion name anger alone or the statement "This text expresses anger". With this paper, we analyze how sensitive a natural language inference-based zero-shot-learning classifier is to such changes to the prompt under consideration of the corpus: How carefully does the prompt need to be selected? We perform experiments on an established set of emotion datasets presenting different language registers according to different sources (tweets, events, blogs) with three natural language inference models and show that indeed the choice of a particular prompt formulation needs to fit to the corpus. We show that this challenge can be tackled with combinations of multiple prompts. Such ensemble is more robust across corpora than individual prompts and shows nearly the same performance as the individual best prompt for a particular corpus.

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。

↑