Analogical Reasoning on Chinese Morphological and Semantic Relations
Computation and Language
2018-08-27 v1 Artificial Intelligence
Abstract
Analogical reasoning is effective in capturing linguistic regularities. This paper proposes an analogical reasoning task on Chinese. After delving into Chinese lexical knowledge, we sketch 68 implicit morphological relations and 28 explicit semantic relations. A big and balanced dataset CA8 is then built for this task, including 17813 questions. Furthermore, we systematically explore the influences of vector representations, context features, and corpora on analogical reasoning. With the experiments, CA8 is proved to be a reliable benchmark for evaluating Chinese word embeddings.
Cite
@article{arxiv.1805.06504,
title = {Analogical Reasoning on Chinese Morphological and Semantic Relations},
author = {Shen Li and Zhe Zhao and Renfen Hu and Wensi Li and Tao Liu and Xiaoyong Du},
journal= {arXiv preprint arXiv:1805.06504},
year = {2018}
}