Analogical Reasoning on Chinese Morphological and Semantic Relations
This provides a domain-specific tool for researchers working on Chinese NLP, though it is incremental as it adapts existing analogical reasoning methods to Chinese.
The paper tackles the problem of analogical reasoning in Chinese by creating a comprehensive dataset (CA8) with 17,813 questions covering 68 morphological and 28 semantic relations, and demonstrates its reliability as a benchmark for evaluating Chinese word embeddings through systematic experiments.
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.