-
Consolidating Commonsense Knowledge
Commonsense reasoning is an important aspect of building robust AI syste...
read it
-
Commonsense Knowledge in Wikidata
Wikidata and Wikipedia have been proven useful for reason-ing in natural...
read it
-
Dimensions of Commonsense Knowledge
Commonsense knowledge is essential for many AI applications, including t...
read it
-
Learning Household Task Knowledge from WikiHow Descriptions
Commonsense procedural knowledge is important for AI agents and robots t...
read it
-
Commonsense reasoning, commonsense knowledge, and the SP theory of intelligence
This paper describes how the "SP theory of intelligence", outlined in an...
read it
-
EQL – an extremely easy to learn knowledge graph query language, achieving highspeed and precise search
EQL, also named as Extremely Simple Query Language, can be widely used i...
read it
-
Truth Validation with Evidence
In the modern era, abundant information is easily accessible from variou...
read it
CSKG: The CommonSense Knowledge Graph
Sources of commonsense knowledge aim to support applications in natural language understanding, computer vision, and knowledge graphs. These sources contain complementary knowledge to each other, which makes their integration desired. Yet, such integration is not trivial because of their different foci, modeling approaches, and sparse overlap. In this paper, we propose to consolidate commonsense knowledge by following five principles. We apply these principles to combine seven key sources into a first integrated CommonSense Knowledge Graph (CSKG). We perform analysis of CSKG and its various text and graph embeddings, showing that CSKG is a well-connected graph and that its embeddings provide a useful entry point to the graph. Moreover, we show the impact of CSKG as a source for reasoning evidence retrieval, and for pre-training language models for generalizable downstream reasoning. CSKG and all its embeddings are made publicly available to support further research on commonsense knowledge integration and reasoning.
READ FULL TEXT
Comments
There are no comments yet.