Towards Interactive Construction of Topical Hierarchy: A Recursive Tensor Decomposition Approach

Automatic construction of user-desired topical hierarchies over large volumes of text data is a highly desirable but chal-lenging task. This study proposes to give users freedom to construct topical hierarchies via interactive operations such as expanding a branch and merging several branches. Exist-ing hierarchical topic modeling techniques are inadequate for this purpose because (1) they cannot consistently preserve the topics when the hierarchy structure is modified; and (2) the slow inference prevents swift response to user requests. In this study, we propose a novel method, called STROD, that allows efficient and consistent modification of topic hi-erarchies, based on a recursive generative model and a scal-able tensor decomposition inference algorithm with theoreti-cal performance guarantee. Empirical evaluation shows that STROD reduces the runtime of construction by several or-ders of magnitude, while generating consistent and quality hierarchies