KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning

By Bill Yuchen Lin, Xinyue Chen, Jamin Chen, Xiang Ren. 2019

528 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Graph Learning, Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Yejin Choi
  3. Percy Liang
  4. Luke S. Zettlemoyer
  5. Jianfeng Gao
  6. Hannaneh Hajishirzi
  7. Caiming Xiong
  8. Noah A. Smith

In Graph Learning

  1. Shirui Pan
  2. Philip S. Yu
  3. Percy Liang
  4. Jure Leskovec
  5. Xiang Ren
  6. Michihiro Yasunaga
  7. Guodong Long
  8. William L. Hamilton

In Knowledge Graphs & Representation

  1. Xiang Ren
  2. Jure Leskovec
  3. Michihiro Yasunaga
  4. Ronan Le Bras
  5. Percy Liang
  6. Hongyu Ren
  7. Yejin Choi
  8. Antoine Bosselut

Citations in the corpus