Abstract
Visual Question Answering (VQA) is gaining momentum for its ability of bridging Computer Vision and Natural Language Processing. VQA approaches mainly rely on Machine Learning algorithms that need to be trained on large annotated datasets. Once trained, a machine learning model is barely portable on a different domain. This calls for agile methodologies for building large annotated datasets from existing resources. The cultural heritage domain represents both a natural application of this task and an extensive source of data for training and validating VQA models. To this end, by using data and models from ArCo, the knowledge graph of the Italian cultural heritage, we generated a large dataset for VQA in Italian and English. We describe the results and the lessons learned by our semi-automatic process for the dataset generation and discuss the employed tools for data extraction and transformation.
This work was supported by the Italian PON project ARS01_00421: “IDEHA - Innovazioni per l’elaborazione dei dati nel settore del Patrimonio Culturale”.
The authors are listed in alphabetical order.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
- 3.
- 4.
A complete list is available on https://github.com/misael77/IDEHAdataset.
- 5.
https://huggingface.co/Helsinki-NLP/opus-mt-it-en and opus-mt-en-it.
- 6.
Available on GitHub https://github.com/misael77/IDEHAdataset.
References
Bongini, P., Becattini, F., Bagdanov, A.D., Del Bimbo, A.: Visual question answering for cultural heritage. In: Proceeding of IOP Conference Series: Materials Science and Engineering (2020)
Carriero, V.A., et al.: ArCo: the Italian cultural heritage knowledge graph. In: Proceeding of ISWC, Part. II, pp. 36–52 (2019)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceeding of NAACL-HLT, pp. 4171–4186 (2019)
Garcia, N., et al.: A dataset and baselines for visual question answering on art. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12536, pp. 92–108. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-66096-3_8
Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. IJCV 123(1), 32–73 (2017)
Malinowski, M., Fritz, M.: A multi-world approach to question answering about real-world scenes based on uncertain input. In: Proceedings of the NIPS, pp. 1682–1690 (2014)
Presutti, V., Blomqvist, E., Daga, E., Gangemi, A.: Pattern-based ontology design. In: Ontology Engineering in a Networked World, pp. 35–64 (2012)
Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Proceedings of the EMNLP (2019)
Seidenari, L., Baecchi, C., Uricchio, T., Ferracani, A., Bertini, M., Bimbo, A.D.: Deep artwork detection and retrieval for automatic context-aware audio guides. TOMM 13(3s), 1–21 (2017)
Wang, P., Wu, Q., Shen, C., Hengel, A.V.D., Dick, A.: Explicit knowledge-based reasoning for visual question answering. In: Proceeding of IJCAI (2017)
Wu, Q., Teney, D., Wang, P., Shen, C., Dick, A., van den Hengel, A.: Visual question answering: a survey of methods and datasets. Comput. Vis. Image Underst. 163, 21–40 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Asprino, L., Bulla, L., Marinucci, L., Mongiovì, M., Presutti, V. (2022). A Large Visual Question Answering Dataset for Cultural Heritage. In: Nicosia, G., et al. Machine Learning, Optimization, and Data Science. LOD 2021. Lecture Notes in Computer Science(), vol 13164. Springer, Cham. https://doi.org/10.1007/978-3-030-95470-3_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-95470-3_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-95469-7
Online ISBN: 978-3-030-95470-3
eBook Packages: Computer ScienceComputer Science (R0)