使用句子编码器进行零样本多标签主题推理（英文版）

英文标题：Zero-Shot Multi-Label Topic Inference with Sentence Encoders中文摘要：利用句子编码器进行零样本主题推断任务时，Sentence-BERT 表现出与其他编码器相比的优越性能，而在效率是首要考虑因素时，通用句子编码器是首选；这一结论得到了对七个不同数据集的广泛实验的支持。英文摘要：Sentence encoders have indeed been shown to achieve superior performances formany downstream text-mining tasks and, thus, claimed to be fairly general.Inspired by this, we performed a detailed study on how to leverage thesesentence encoders for the "zero-shot topic inference" task, where the topicsare defined/provided by the