Analogical Reasoning on Chinese Morphological and Semantic Relations

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.

References in corpus (4)

• Enriching Word Vectors with Subword Information
• A Uniform Approach to Analogies, Synonyms, Antonyms, and Associations
• Learning Chinese Word Representations From Glyphs Of Characters
• BagPack: A general framework to represent semantic relations

Cited by in corpus (7)

• One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profiles
• BERT-based Financial Sentiment Index and LSTM-based Stock Return Predictability
• Fake News Detection as Natural Language Inference
• QSAN: A Quantum-probability based Signed Attention Network for Explainable False Information Detection
• LSICC: A Large Scale Informal Chinese Corpus
• Latent Suicide Risk Detection on Microblog via Suicide-Oriented Word Embeddings and Layered Attention
• Controllable Gradient Item Retrieval