ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
This work addresses the need for better understanding of language meanings in NLP applications, though it is incremental as an update to an existing resource.
The authors tackled the problem of improving machine learning about language by introducing ConceptNet 5.5, an open multilingual knowledge graph that enhances NLP techniques like word embeddings, resulting in state-of-the-art performance on word relatedness evaluations and improvements in applications such as solving SAT-style analogies.
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.