@InProceedings{li-yang-ma:2020:LREC,
  author    = {Li, Peng-Hsuan  and  Yang, Tsan-Yu  and  Ma, Wei-Yun},
  title     = {CA-EHN: Commonsense Analogy from E-HowNet},
  booktitle      = {Proceedings of The 12th Language Resources and Evaluation Conference},
  month          = {May},
  year           = {2020},
  address        = {Marseille, France},
  publisher      = {European Language Resources Association},
  pages     = {2984--2990},
  abstract  = {Embedding commonsense knowledge is crucial for end-to-end models to generalize inference beyond training corpora. However, existing word analogy datasets have tended to be handcrafted, involving permutations of hundreds of words with only dozens of pre-defined relations, mostly morphological relations and named entities. In this work, we model commonsense knowledge down to word-level analogical reasoning by leveraging E-HowNet, an ontology that annotates 88K Chinese words with their structured sense definitions and English translations. We present CA-EHN, the first commonsense word analogy dataset containing 90,505 analogies covering 5,656 words and 763 relations. Experiments show that CA-EHN stands out as a great indicator of how well word representations embed commonsense knowledge. The dataset is publicly available at \url{https://github.com/ckiplab/CA-EHN}.},
  url       = {https://www.aclweb.org/anthology/2020.lrec-1.365}
}