Aiming at the identification of Chinese fine-grained implicit discourse relation and taking the directionality characteristic in account, the authors propose a feature learning algorithm based on the distant supervision to label explicit discourse data automatically. The relative position information between conjunction and words are applied to train the intensive word representation. Then the rhetorical function of words and the directionality of relations are encoded into the representation of intensive words, which is applied to the relation classification of fine-grained implicit discourses. From the experimental studies of the proposed approach, the classification accuracy reaches 49.79%, which are better than those approaches neglecting the directionality of discourse relations.