Sememe-Based Lexical Knowledge Representation Learning

Abstract

Linguistic and commonsense knowledge bases describe knowledge in formal and structural languages. Such knowledge can be easily leveraged in modern natural language processing systems. In this chapter, we introduce one typical kind of linguistic knowledge (sememe knowledge) and a sememe knowledge base named HowNet. In linguistics, sememes are defined as the minimum indivisible units of meaning. We first briefly introduce the basic concepts of sememe and HowNet. Next, we introduce how to model the sememe knowledge using neural networks. Taking a step further, we introduce sememe-guided knowledge applications, including incorporating sememe knowledge into compositionality modeling, language modeling, and recurrent neural networks. Finally, we discuss sememe knowledge acquisition for automatically constructing sememe knowledge bases and representative real-world applications of HowNet.

A Novel Approach to Semic Analysis: Extraction of Atoms of Meaning to Study Polysemy and Polyreferentiality

“…Furthermore, a diverse perspective is presented in the contribution of Ye et al (2022, p. 128), which focuses on conferring a structured organization to sememes, with the specific purpose of "predicting a sememe tree with hierarchical structure rather than a set of sememes". In addition, Qin et al (2023) tackle the activity of sememe knowledge modeling by utilizing neural networks. Moreover, in a recent study by Zhang et al (2023Zhang et al ( , p. 2790, an innovative method aimed at "aligning BabelNet synsets to HowNet senses" is proposed.…”