“…In the literature, most of previous studies focused on English, with only a few on Chinese. Compared with traditional feature-based methods (Pitler et al, 2009;Lin et al, 2009;Kong and Zhou, 2017) that directly rely on feature engineering, recent neural network models (Liu et al, 2017;Qin et al, 2017;Guo et al, 2018;Bai and Zhao, 2018) can capture deeper semantic cues and learn better representations (Zhang et al, 2015). In particular, most neural network-based methods encode arguments using variants of Bi-LSTM or CNN (Qin et al, 2016;Guo et al, 2018) and propose various models (e.g., the gated relevance network, the encoder-decoder model, and interactive attention) to measure the semantic relevance (Chen et al, 2016;Cianflone and Kosseim, 2018;Guo et al, 2018) Due to the large differences between the hypotactic English language and the paratactic Chinese language, English-based models, which rely heavily on sentence-level representations, may not function well on Chinese.…”