The neural components in deep learning framework are crucial for the performance of many natural language processing tasks.So far there is no systematic work to investigate the influence of neural components on the performance of implicit discourse relation recognition.To address it,in this work we compare many different components and build two implicit discourse parsers base on the sequence and structure of sentence respectively.Experimental results show due to different linguistic features,the neural components have different effects in English and Chinese.Besides,our models achieve state-of-the-art performance on CoNLL-2016 English and Chinese datasets.