Exploring Semantic Capacity of Terms

TL;DR

This paper introduces a model to quantify the semantic capacity of terms based on their co-occurrence in large text corpora, aiding natural language processing tasks.

Contribution

It proposes a novel two-step model for evaluating semantic capacity of terms, validated through extensive experiments across multiple fields.

Findings

Model effectively measures semantic capacity of terms.

Experiments show alignment with human judgments.

Model outperforms baseline approaches.

Abstract

We introduce and study semantic capacity of terms. For example, the semantic capacity of artificial intelligence is higher than that of linear regression since artificial intelligence possesses a broader meaning scope. Understanding semantic capacity of terms will help many downstream tasks in natural language processing. For this purpose, we propose a two-step model to investigate semantic capacity of terms, which takes a large text corpus as input and can evaluate semantic capacity of terms if the text corpus can provide enough co-occurrence information of terms. Extensive experiments in three fields demonstrate the effectiveness and rationality of our model compared with well-designed baselines and human-level evaluations.