%0 Journal Article %A XU Shaoyang %A JIANG Feng %A LI Peifeng %T Topic Segmentation via Discourse Structure Graph Network %D 2021 %R %J Journal of Chinese Information Processing %P 17-27 %V 35 %N 12 %X Topic segmentation, as one of the classic tasks in the field of natural language processing, is to segment the input discourse into paragraphs with continuous semantics. Previous works used word frequencybased, latentbased, sequentialbased, and Transformerbased methods to encode sentences, ignoring modeling global semantic information of the discourse. This paper proposes to use Discourse Structure Graph Network to encode sentences for a sentence representation with the global information of the discourse. In detail, the model firstly constructs a single graph for each discourse, which contains all sentences and word nodes of it as well as the adjacency information between them. The model then uses Gated Graph Neural Networks to iterate the graph that gets the sentence representation with the global information of the discourse. They are finally fed to the Bi-LSTM layer to predict the segmentation points. The experimental results demonstrate that the model gets a more suitable sentence representation than other baselines for topic segmentation and achieves the best performance on various popular datasets. %U http://jcip.cipsc.org.cn/EN/abstract/article_3228.shtml