KagNet swMATH ID: 44702 Software Authors: Bill Yuchen Lin, Xinyue Chen, Jamin Chen, Xiang Ren Description: KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning. Commonsense reasoning aims to empower machines with the human ability to make presumptions about ordinary situations in our daily life. In this paper, we propose a textual inference framework for answering commonsense questions, which effectively utilizes external, structured commonsense knowledge graphs to perform explainable inferences. The framework first grounds a question-answer pair from the semantic space to the knowledge-based symbolic space as a schema graph, a related sub-graph of external knowledge graphs. It represents schema graphs with a novel knowledge-aware graph network module named KagNet, and finally scores answers with graph representations. Our model is based on graph convolutional networks and LSTMs, with a hierarchical path-based attention mechanism. The intermediate attention scores make it transparent and interpretable, which thus produce trustworthy inferences. Using ConceptNet as the only external resource for Bert-based models, we achieved state-of-the-art performance on the CommonsenseQA, a large-scale dataset for commonsense reasoning. Homepage: https://arxiv.org/abs/1909.02151 Source Code: https://github.com/INK-USC/KagNet Related Software: GPT-3; Tensor2Tensor; BERT; GloVe; word2vec; RoBERTa; ALBERT; ConceptNet; Graph2Seq; PTE; GCC; AlexNet; SemSUM; Linformer; Event2Mind; JGibbLDA; KATE; GraphIE; aNMM; PyTorch Cited in: 3 Documents all top 5 Cited by 11 Authors 1 Camacho-Collados, José 1 Gao, Hanning 1 Guo, Xiaojie 1 Jorge, Alípio Mário 1 Li, Shucheng 1 Long, Bo 1 Loureiro, Daniel 1 Pei, Jian 1 Shen, Kai 1 Wu, Lingfei 1 Yang, Zhun Cited in 2 Serials 1 Artificial Intelligence 1 Foundations and Trends in Machine Learning Cited in 1 Field 3 Computer science (68-XX) Citations by Year