Skip to main content

Research Repository

Advanced Search

Outputs (7)

A mixture-of-experts model for learning multi-facet entity embeddings (2020)
Conference Proceeding
Alshaikh, R., Bouraoui, Z., Jeawak, S., & Schockaert, S. (2020). A mixture-of-experts model for learning multi-facet entity embeddings. In Proceedings of the 28th International Conference on Computational Linguistics (5124-5135)

Various methods have already been proposed for learning entity embeddings from text descriptions. Such embeddings are commonly used for inferring properties of entities, for recommendation and entity-oriented search, and for injecting background know... Read More about A mixture-of-experts model for learning multi-facet entity embeddings.

Cardiff University at SemEval-2020 Task 6: Fine-tuning BERT for Domain-Specific Definition Classification (2020)
Conference Proceeding
Jeawak, S. S., Espinosa-Anke, L., & Schockaert, S. (2020). Cardiff University at SemEval-2020 Task 6: Fine-tuning BERT for Domain-Specific Definition Classification. In Proceedings of the Fourteenth Workshop on Semantic Evaluation (361-366)

We describe the system submitted to SemEval-2020 Task 6, Subtask 1. The aim of this subtask is to predict whether a given sentence contains a definition or not. Unsurprisingly, we found that strong results can be achieved by fine-tuning a pre-trained... Read More about Cardiff University at SemEval-2020 Task 6: Fine-tuning BERT for Domain-Specific Definition Classification.

Predicting the environment from social media: A collective classification approach (2020)
Journal Article
Jeawak, S. S., Jones, C. B., & Schockaert, S. (2020). Predicting the environment from social media: A collective classification approach. Computers, Environment and Urban Systems, 82, https://doi.org/10.1016/j.compenvurbsys.2020.101487

We propose a method which uses Flickr tags to predict a wide variety of environmental features, such as climate data, land cover categories, species occurrence, and human assessments of scenicness. The role of Flickr tags in our method is two-fold. F... Read More about Predicting the environment from social media: A collective classification approach.

Predicting environmental features by learning spatiotemporal embeddings from social media (2019)
Journal Article
Jeawak, S. S., Jones, C. B., & Schockaert, S. (2020). Predicting environmental features by learning spatiotemporal embeddings from social media. Ecological Informatics, 55, https://doi.org/10.1016/j.ecoinf.2019.101031

Spatiotemporal modelling is an important task for ecology. Social media tags have been found to have great potential to assist in predicting aspects of the natural environment, particularly through the use of machine learning methods. Here we propose... Read More about Predicting environmental features by learning spatiotemporal embeddings from social media.

Embedding geographic locations for modelling the natural environment using flickr tags and structured data (2019)
Conference Proceeding
Jeawak, S. S., Jones, C. B., & Schockaert, S. (2019). Embedding geographic locations for modelling the natural environment using flickr tags and structured data. In Advances in Information Retrieval. , (51-66). https://doi.org/10.1007/978-3-030-15712-8_4

Meta-data from photo-sharing websites such as Flickr can be used to obtain rich bag-of-words descriptions of geographic locations, which have proven valuable, among others, for modelling and predicting ecological features. One important insight from... Read More about Embedding geographic locations for modelling the natural environment using flickr tags and structured data.

Mapping wildlife species distribution with social media: Augmenting text classification with species names (2018)
Journal Article
Jeawak, S. S., Jones, C. B., & Schockaert, S. (2018). Mapping wildlife species distribution with social media: Augmenting text classification with species names. LIPIcs, 114, https://doi.org/10.4230/LIPIcs.GIScience.2018.34

© Shelan S. Jeawak, Christopher B. Jones, and Steven Schockaert. Social media has considerable potential as a source of passive citizen science observations of the natural environment, including wildlife monitoring. Here we compare and combine two ma... Read More about Mapping wildlife species distribution with social media: Augmenting text classification with species names.

Using flickr for characterizing the environment: An exploratory analysis (2017)
Journal Article
Jeawak, S. S., Jones, C. B., & Schockaert, S. (2017). Using flickr for characterizing the environment: An exploratory analysis. LIPIcs, 86, 21:1--21:13. https://doi.org/10.4230/LIPIcs.COSIT.2017.21

© Shelan S. Jeawak, Christopher B. Jones, and Steven Schockaert. The photo-sharing website Flickr has become a valuable informal information source in disciplines such as geography and ecology. Some ecologists, for instance, have been manually analys... Read More about Using flickr for characterizing the environment: An exploratory analysis.