Do Sentence Transformers Learn Quasi-Geospatial Concepts from General Text?

arXiv:2404.04169v1 Announce Type: cross
Abstract: Sentence transformers are language models designed to perform semantic search. This study investigates the capacity of sentence transformers, fine-tuned on general question-answering datasets for asymmetric semantic search, to associate descriptions of human-generated routes across Great Britain with queries often used to describe hiking experiences. We find that sentence transformers have some zero-shot capabilities to understand quasi-geospatial concepts, such as route types and difficulty, suggesting their potential utility for routing recommendation systems.

abstract arxiv britain capacity concepts cs.cl cs.lg datasets general generated geospatial great britain hiking human language language models learn queries question routes search semantic study text transformers type