ConceptNet 5.5: An Open Multilingual Graph of General Knowledge

TL;DR

ConceptNet 5.5 is a comprehensive, multilingual knowledge graph designed to enhance natural language understanding in machine learning by integrating structured general knowledge with word embeddings, leading to improved NLP applications.

Contribution

This paper introduces ConceptNet 5.5, a new version of the knowledge graph optimized for modern NLP techniques, combining diverse data sources to improve language understanding.

Findings

Enhanced performance on word relatedness tasks

Improved results on SAT-style analogy questions

Better integration with word embeddings for NLP applications

Abstract

Machine learning about language can be improved by supplying it with specific knowledge and sources of external information. We present here a new version of the linked open data resource ConceptNet that is particularly well suited to be used with modern NLP techniques such as word embeddings. ConceptNet is a knowledge graph that connects words and phrases of natural language with labeled edges. Its knowledge is collected from many sources that include expert-created resources, crowd-sourcing, and games with a purpose. It is designed to represent the general knowledge involved in understanding language, improving natural language applications by allowing the application to better understand the meanings behind the words people use. When ConceptNet is combined with word embeddings acquired from distributional semantics (such as word2vec), it provides applications with understanding that they would not acquire from distributional semantics alone, nor from narrower resources such as WordNet or DBPedia. We demonstrate this with state-of-the-art results on intrinsic evaluations of word relatedness that translate into improvements on applications of word vectors, including solving SAT-style analogies.