Towards Olfactory Information Extraction from Text: A Case Study on Detecting Smell Experiences in Novels

Ryan Brate, Paul Groth, Marieke van Erp


Abstract
Environmental factors determine the smells we perceive, but societal factors factors shape the importance, sentiment and biases we give to them. Descriptions of smells in text, or as we call them ‘smell experiences’, offer a window into these factors, but they must first be identified. To the best of our knowledge, no tool exists to extract references to smell experiences from text. In this paper, we present two variations on a semi-supervised approach to identify smell experiences in English literature. The combined set of patterns from both implementations offer significantly better performance than a keyword-based baseline.
Anthology ID:
2020.latechclfl-1.18
Original:
2020.latechclfl-1.18v1
Version 2:
2020.latechclfl-1.18v2
Volume:
Proceedings of the The 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature
Month:
December
Year:
2020
Address:
Online
Venues:
CLFL | COLING | LaTeCH | LaTeCHCLfL
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
147–155
Language:
URL:
https://aclanthology.org/2020.latechclfl-1.18
DOI:
Bibkey:
Cite (ACL):
Ryan Brate, Paul Groth, and Marieke van Erp. 2020. Towards Olfactory Information Extraction from Text: A Case Study on Detecting Smell Experiences in Novels. In Proceedings of the The 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pages 147–155, Online. International Committee on Computational Linguistics.
Cite (Informal):
Towards Olfactory Information Extraction from Text: A Case Study on Detecting Smell Experiences in Novels (Brate et al., LaTeCHCLfL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.latechclfl-1.18.pdf