SoNLP-DP System for ConLL-2016 Chinese Shallow Discourse Parsing

This paper describes our submission to the CoNLL-2016 shared task (Xue et al., 2016) on end-to-end Chinese shallow discourse parsing. We decompose the endto-end process into four steps. Firstly, we define a syntactically heuristic algorithm to identify elementary discourse units (EDUs) and further to recognize valid EDU pairs. Secondly, we recognize explicit discourse connectives. Thirdly, we link each explicit connective to valid EDU pairs to obtain explicit discourse relations. For those valid EDU pairs not linked to any explicit connective, they become non-explicit discourse relations.1 Finally, we assign each discourse relation, either explicit or non-explicit with a discourse sense. Our system is evaluated on the closed track of the CoNLL2016 shared task and achieves 35.54% and 23.46% in F1-measure on the official test set and blind test set, respectively.