Selection Strategies for Commonsense Knowledge
This work addresses a domain-specific issue in automated reasoning by improving selection strategies for commonsense knowledge bases, but it appears incremental as it builds on existing statistical techniques.
The paper tackles the problem of selecting relevant commonsense knowledge for theorem proving by introducing a vector-based selection strategy using word embeddings, and demonstrates its usefulness in a case study.
Selection strategies are broadly used in first-order logic theorem proving to select those parts of a large knowledge base that are necessary to proof a theorem at hand. Usually, these selection strategies do not take the meaning of symbol names into account. In knowledge bases with commonsense knowledge, symbol names are usually chosen to have a meaning and this meaning provides valuable information for selection strategies. We introduce the vector-based selection strategy, a purely statistical selection technique for commonsense knowledge based on word embeddings. We compare different commonsense knowledge selection techniques for the purpose of theorem proving and demonstrate the usefulness of vector-based selection with a case study.