论文标题
零击分类器标签描述的无监督排名和汇总
Unsupervised Ranking and Aggregation of Label Descriptions for Zero-Shot Classifiers
论文作者
论文摘要
基于标签描述的零击文本分类器将输入文本和一组标签嵌入了相同的空间：然后可以使用诸如余弦相似性之类的措施来选择与预测标签的输入文本最相似的标签描述。在真实的零镜设置中，设计良好的标签描述是具有挑战性的，因为没有开发集可用。受分歧分歧学习的文献的启发，我们研究了如何将重复评级分析的概率模型用于以无监督的方式选择最佳的标签描述。我们在一组不同的数据集和任务（情感，主题和立场）上评估我们的方法。此外，我们表明可以汇总多个嘈杂的标签描述以提高性能。
Zero-shot text classifiers based on label descriptions embed an input text and a set of labels into the same space: measures such as cosine similarity can then be used to select the most similar label description to the input text as the predicted label. In a true zero-shot setup, designing good label descriptions is challenging because no development set is available. Inspired by the literature on Learning with Disagreements, we look at how probabilistic models of repeated rating analysis can be used for selecting the best label descriptions in an unsupervised fashion. We evaluate our method on a set of diverse datasets and tasks (sentiment, topic and stance). Furthermore, we show that multiple, noisy label descriptions can be aggregated to boost the performance.
