CA-EHN: Commonsense Word Analogy from E-HowNet

Peng-Hsuan Li, Tsan-Yu Yang, Wei-Yun Ma

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 https://github.com/ckiplab/CA-EHN.
BibTeX
@inproceedings{li2020ca,
  author = {Peng-Hsuan Li and Tsan-Yu Yang and Wei-Yun Ma},
  title = {{CA-EHN: Commonsense Word Analogy from E-HowNet}},
  booktitle = {LREC},
  year = {2020},
  url = {https://openreview.net/forum?id=8TCeQkiHraa},
}

Loading related content...

Figure