Scent Mining: Extracting Olfactory Events, Smell Sources and Qualities

Abstract

Olfaction is a rather understudied sense compared to the other human senses. In NLP, however, there have been recent attempts to develop taxonomies and benchmarks specifically designed to capture smell-related information. In this work, we further extend this research line by presenting a supervised system for olfactory information extraction in English. We cast this problem as a token classification task and build a system that identifies smell words, smell sources and qualities. The classifier is then applied to a set of English historical corpora, covering different domains and written in a time period between the 15th and the 20th Century. A qualitative analysis of the extracted data shows that they can be used to infer interesting information about smelly items such as tea and tobacco from a diachronical perspective, supporting historical investigation with corpus-based evidence.

Scent and Sensibility: Perception Shifts in the Olfactory Domain

“…As regards the development of structured re-sources to investigate the evolution of sensory language, Menini et al (2022a) present a multilingual taxonomy for olfactory-related terms, which was created semi-automatically, with the goal to describe the evolution of odours and smell sources' descriptions. Furthermore, in Menini et al (2022b), the authors present a multilingual benchmark, manually annotated with smell-related information, to support the development of olfactory information extraction systems.…”