论文标题
无监督的表达性规则提供了解释性，并协助人类专家抓住新领域
Unsupervised Expressive Rules Provide Explainability and Assist Human Experts Grasping New Domains
论文作者
论文摘要
接近新数据可能是非常威慑的。您不知道如何在其中实现您的兴趣类别，通常没有标记的数据，并且域适应方法的性能不令人满意。 旨在帮助领域专家通过新的语料库完成新任务的第一步，我们提出了一种无监督的方法，以揭示复杂的规则，以通过其突出类别（或方面）聚集未探索的语料库。 这些规则是可读的，因此提供了一种重要的成分，该成分最近已供应 - 解释性。每个规则都为其簇在一起的所有文本的共同点提供了解释。 我们对这些规则在识别目标类别的实用性以及评估其可解释性的用户研究中进行了广泛的评估。
Approaching new data can be quite deterrent; you do not know how your categories of interest are realized in it, commonly, there is no labeled data at hand, and the performance of domain adaptation methods is unsatisfactory. Aiming to assist domain experts in their first steps into a new task over a new corpus, we present an unsupervised approach to reveal complex rules which cluster the unexplored corpus by its prominent categories (or facets). These rules are human-readable, thus providing an important ingredient which has become in short supply lately - explainability. Each rule provides an explanation for the commonality of all the texts it clusters together. We present an extensive evaluation of the usefulness of these rules in identifying target categories, as well as a user study which assesses their interpretability.
