Enhancing Sentence Ordering by Hierarchical Topic Modeling for Multi-document Summarization

Abstract

The sentence ordering is a difficult but very important task in multi-document summarization. With the aim of producing a coherent and legible summary for multiple documents, this study proposes a novel approach that is built upon a hierarchical topic model for automatic evaluation of sentence ordering. By learning topic correlations from the topic hierarchies, this model is able to automatically evaluate sentences to find a plausible order to arrange them for generating a more readable summary. The experimental results demonstrate that our proposed approach can improve the summarization performance and present a significant enhancement on the sentence ordering for multi-document summarization. In addition, the experimental results show that our model can automatically analyze the topic relationships to infer a strategy for sentence ordering. Human evaluations justify that the generated summaries, which implement this strategy, demonstrate a good linguistic performance in terms of coherence, readability, and redundancy.