@article{Guo_He_Dang_Wang_2020, title={Working Memory-Driven Neural Networks with a Novel Knowledge Enhancement Paradigm for Implicit Discourse Relation Recognition}, volume={34}, url={https://ojs.aaai.org/index.php/AAAI/article/view/6287}, DOI={10.1609/aaai.v34i05.6287}, abstractNote={<p>Recognizing implicit discourse relation is a challenging task in discourse analysis, which aims to understand and infer the latent relations between two discourse arguments, such as temporal, comparison. Most of the present models largely focus on learning-based methods that utilize only intra-sentence textual information to identify discourse relations, ignoring the wider contexts beyond the discourse. Moreover, people comprehend the meanings and the relations of discourses, heavily relying on their interconnected working memories (e.g., instant memory, long-term memory). Inspired by this, we propose a <strong>K</strong>nowledge-Enhanced <strong>A</strong>ttentive <strong>N</strong>eural <strong>N</strong>etwork (KANN) framework to address these issues. Specifically, it establishes a mutual attention matrix to capture the reciprocal information between two arguments, as instant memory. While implicitly stated knowledge in the arguments is retrieved from external knowledge source and encoded as inter-words semantic connection embeddings to further construct knowledge matrix, as long-term memory. We devise a novel paradigm with two ways by the collaboration of the memories to enrich the argument representation: 1) integrating the knowledge matrix into the mutual attention matrix, which implicitly maps knowledge into the process of capturing asymmetric interactions between two discourse arguments; 2) directly concatenating the argument representations and the semantic connection embeddings, which explicitly supplements knowledge to help discourse understanding. The experimental results on the PDTB also show that our KANN model is effective.</p>}, number={05}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Guo, Fengyu and He, Ruifang and Dang, Jianwu and Wang, Jian}, year={2020}, month={Apr.}, pages={7822-7829} }