Text Archives - Page 5 of 5

28 May 202225 March 2021 Sara Tonelli

Linguists have observed in several studies that languages seem to have a smaller vocabulary to describe smells compared to other senses. Odours are often described borrowing terms from other senses, for example “sweet” or “fresh”, or relying on qualities of objects, like “musky” or “metallic”. On the other hand, other domains such as perfumery and oenology make use of extremely precise and structured repositories of terms and qualities used by professionals for describing perfumes and wines from an olfactory perspective. One of the goals of the text processing team of Odeuropa is to understand these phenomena and analyse whether there are differences across languages in the way in which odours are described. Is the smell-related dimension of the olfactory vocabulary something that is more evident in some languages? For example, does Slovenian, which is a Balto-Slavic language, have different characteristics in terms of olfactory vocabulary compared to Romance or Germanic languages like Italian and English? If ‘yes’, are there historical or cultural reasons for this?

We aim to address these questions using text mining techniques by processing large amounts of digitised texts covering four centuries and automatically extracting the terminology pertaining to smell. To this purpose, we are collecting freely available texts issued between 1650 and 1925 and covering different domains, in the seven project languages (English, German, French, Latin, Dutch, Slovene, and Italian). These texts range from travel literature to scientific texts and medical records. This process takes a long time because after preparing a detailed list of available sources, the data need to be downloaded, cleaned, standardised and accompanied with the correct metadata. While the Odeuropa multilingual corpus is being completed, we are testing different approaches to terminology extraction. Our testbed is the GoogleNgram repository, a large collection of n-grams (i.e. word sequences) extracted from Google Books divided by year of publication.

The n-grams cover the period of interest for Odeuropa, allowing us to perform preliminary analyses aimed at comparing terminology in multiple languages over time. In this analysis, we start from a small list of smell-related words provided by Odeuropa domain experts such as “odour”, “smelly”, “reek”. We then extract for different time periods the terms that have the highest association strength with the smell words, meaning that they tend to appear together more frequently than usual. Terms co-occurring with the smell words provide a concise overview of the semantic domains associated with odours over time, and make comparisons across languages possible. For example, we can analyse terms related to “odor” (English) , “odore” (Italian) and “reuk” (Dutch) for the n-grams between 1900 and 1925. These are displayed in the picture below, where the bubble dimension is proportional to the association strength. Some concepts mentioned in relation to smell seem to be present for the three languages, for example flowers, tobacco and sanctity. On the other hand, in English, medical-related terms are more present, while for Italian food and beverages are mentioned (see also “sapore” / “taste”) and for Dutch, fishing seems to play a role in the word association. For now, our results are too preliminary to draw conclusions on olfactory terminology, but we are really looking forward to understanding what texts from the past tell us about odours and their story.

Google ngram visualisation — Terms extracted from Google N-grams that are more frequently used associated with “odor”, “odore” and “reuk”.

25 March 202114 December 2020 Marieke van Erp

This weekend, Marieke van Erp presented a paper on extracting olfactory information from English text at the 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, organised in conjunction with COLING 2020. The paper was presented in a poster presentation, sadly not in Barcelona, but in a gather.town session.

For this paper, we did a first set of experiments into how we can best recognise references to smell in texts, which is an important task in Odeuropa’s Work Package 3. For this paper, we first created an annotated dataset, i.e. a set of texts in which humans (= Odeuropa team members) marked whether the text described a reference to a smell. We then created patterns based on a set of smell related words from the Cambridge dictionary of English to such as ‘smells like X’ and ‘a Y fragrance’ where X and Y can stand for nouns and adjectives. We ran the patterns over a large set of texts to see if we could find more expressions referring to smells in text as compared to only using the dictionary smell keywords, and our experiments showed that patterns indeed worked better than keywords. In Odeuropa, we will further build on this, as well as try out other methods (such as machine learning) to recognise references to smells in Latin, English, Italian, German, French, Dutch, and Slovene texts from 1600 – 1920 across different genres.

This research paper was based on the Ryan Brate’s MSc thesis work which he did for the University of Amsterdam’s Data Science degree programme under the supervision of prof. dr. Paul Groth and dr. Marieke van Erp. Full citation:

Brate, Ryan, Paul Groth, and Marieke van Erp. “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, pp. 147-155. 2020.