Automatic topic labeling using graph-based pre-trained neural embedding

Abstract

It is necessary to reduce the cognitive overhead of interpreting the native topic term list of the Latent Dirichlet Allocation (LDA) style topic model. In this regard, automatic topic labeling has become an effective approach to generate meaningful alternative representations of topics discovered for end-users. In this study, we introduced a novel two-phase neural embedding framework with the redundancy-aware graph-based ranking process. It demonstrated how pre-trained neural embedding could be usefully applied in topic terms, sentence presentations, and automatic topic labeling tasks. Moreover, reranking the topic terms optimized the discovered topics with fewer yet more representative terms while retaining the topic information integrality and fidelity. It further decreased the burden of computation caused by neural embedding and improved the overall effectiveness of the labeling system. Compared with the prevailing state-of-the-art and classical labeling systems, our efficient model boosted the quality of the topic labels generated and discovered more meaningful topic labels.