Measuring Semantic Similarity and Relatedness with Distributional and Knowledge-based Approaches

Christoph LOFI
2015 Information and Media Technologies  
This paper provides a survey of different techniques for measuring semantic similarity and relatedness of word pairs. This covers both knowledge-based approaches exploiting taxonomies like WordNet, and corpus-based approaches which rely on distributional statistics. We introduce these techniques, provide evaluations of their result performance, and discuss their merits and shortcomings. A special focus is on word embeddings, a new technique which recently became popular with the AI community.
more » ... ile word embeddings are not fully understood yet, they show promising results for similarity tasks, and may also be suitable for capturing significantly more complex features like relational similarity.
doi:10.11185/imt.10.493 fatcat:emuwh4pianaidnuib6fwd2jxlm