Semantic Relatedness Measure

Context:
- It takes into account antonymy and meronymy.
- It can be mathematically expressed by $SRM(w_1,w_2)=b$, where $w_1$ and $w_2$ are two linguistic sequences and $b$ is a semantic relatedness score (usually a percentage or number between 0 and 1).
- It can be generated by a Semantic Relatedness Modelling Task.
Example(s):
- a Semantic Word Relatedness Measure such a:
- $SRM(coffee, mug) \ne 0$, i.e. coffee and mug are semantically related, although they are not semantically similar.
- a Semantic Sentence Relatedness Measure,
- …
Counter-Example(s):
- Semantic Similarity Measure.
See: Natural Language Processing, Natural Language Understanding, Language Model, Semantics, Syntactic.

References

(Chandrasekaran & Mago, 2021) ⇒ Dhivya Chandrasekaran, and Vijay Mago. (2021). “Evolution of Semantic Similarity - A Survey.” In: ACM Computing Surveys, 54(2).
- QUOTE: Semantic similarity methods usually give a ranking or percentage of similarity between texts, rather than a binary decision as similar or not similar. Semantic similarity is often used synonymously with semantic relatedness. However, semantic relatedness not only accounts for the semantic similarity between texts but also considers a broader perspective analyzing the shared semantic properties of two words. For example, the words ‘coffee’ and ‘mug’ may be related to one another closely, but they are not considered semantically similar whereas the words ‘coffee’ and ‘tea’ are semantically similar. Thus, semantic similarity may be considered, as one of the aspects of semantic relatedness. The semantic relationship including similarity is measured in terms of semantic distance, which is inversely proportional to the relationship (...)