Submit your work: First International Workshop on Multisensory Data & Knowledge

Together with the Polifonia team, we’re organising a workshop on Multisensory Data & Knowledge to take place in conjunction with the Language Data and Knowledge conference in September. The goal of this workshop is to advance our understanding of how smells and music are represented in texts and structured data. The topics we want to address revolve around extracting references to smells, music, context, and visual information from text as well as relevant data describing their cultural, historical and political context, and model them in the form of interlinked knowledge graphs. This research has a strong interdisciplinary character, hence the workshop has the potential to attract researchers from diverse disciplines from both social sciences and humanities and computer science. Its potential impact is significant to many application areas including: preservation and valorisation of cultural heritage, data-driven policy making in cultural heritage, urban planning, artistic performances, applications for scholars in musicology and history, applications for museums, innovation in teaching, maintenance and exploitation of large catalogues, archives and libraries.

We invite long papers between 10 and 15 pages and short papers between 6 to 8 pages. Note that this workshop is organised following the computer science conference/publication culture, so initial submissions are expected to be in a near publishable state and will be reviewed by three reviewers. Accepted papers will be published through ceur-ws.org.

Submission deadline: 23 April 2021, the workshop will take place on 1 September.

More information on the workshop: https://odeuropa.github.io/mdk21/

Opening the fragrant conversation

When we announced Odeuropa last November, we couldn’t have dreamed that it would be received with so much enthusiasm. As the research teams kick off the programme, we’d like to share an overview of the international response to Odeuropa’s launch from the media, research community and general public, which is already developing into a wider conversation into the relevance of smell in our lives and how the idea of olfactory heritage resonates with a large variety of audiences.

Not only in Europe, but around the globe, the project was widely covered by feature articles and in-depth interviews, for instance by the Spanish scientific news agency,  Le Monde, La Stampa, La RepubblicaDeutschland Radio, NPO Radio 1, Delo, El PaísCNET, and CNN. The Guardian, The New York Times and The Sunday Times reported on our research aims and innovative approach, along with the BBC.

From a video by Indonesian YouTube channel The Shiny Peanut (+12M subscribers) which animated members of our research team to a thoughtful reflection by the Times of Israel of the power of scent to overcome ignorance and communicate on a subject as complex as the Holocaust, we were delighted to see that so many people across the world share our curiosity to explore the potential of olfactory heritage.

Shiny Peanut
The Shiny Peanut, YouTube.

People shared the scents they considered meaningful in comments about nostalgic memories or fragrant experiences, and even reflections about covid-related loss of smell.  The New York Times, inspired by Odeuropa, invited their readers to imagine a museum of smells and worked with artist Janie Korn to produce a series of one-off candles inspired by the project

We are honoured and intensely happy to engage with these and the many other responses we received. In the next weeks and months, we will start to explore how we can accommodate new collaborations and keep expanding our network. Please stay tuned for information here on our website and via Twitter @odeuropa

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

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.