Accessible Cultural Heritage through Explainable Artificial Intelligence

Abstract

Ethics Guidelines for Trustworthy AI advocate for AI technology that is, among other things, more inclusive. Explainable AI (XAI) aims at making state of the art opaque models more transparent, and defends AI-based outcomes endorsed with a rationale explanation, i.e., an explanation that has as target the non-technical users. XAI and Responsible AI principles defend the fact that the audience expertise should be included in the evaluation of explainable AI systems. However, AI has not yet reached all public and audiences, some of which may need it the most. One example of domain where accessibility has not much been influenced by the latest AI advances is cultural heritage. We propose including minorities as special user and evaluator of the latest XAI techniques. In order to define catalytic scenarios for collaboration and improved user experience, we pose some challenges and research questions yet to address by the latest AI models likely to be involved in such synergy.

CulturAI: Semantic Enrichment of Cultural Data Leveraging Artificial Intelligence

“…Remaining within the artificial intelligence area, authors in [8] discuss some challenges and research questions to be addressed by the latest explainable artificial intelligence (XAI) models. Fairness, accountability, and transparency in machine learning are the first topics where specific challenges defined by the authors revolve around.…”

“…As Deep Learning is a flourishing strategy in image and video captioning [24], we exploited a deep neural network-based Image Captioning framework to label each candidate frame f C ∈ CF with an appropriate caption. In detail, CulturAI embeds an Image Captioning framework 8 compliant with the architecture proposed by Xu et al [27]. The framework adopts a convolutional neural network to extract from each candidate frame its visual fea-tures, which are subsequently decoded into human-friendly sentences by an LSTM recurrent neural network.…”

“…In particular, we discuss here our currently ongoing developments and future directions, focusing the attention on those improvements aimed at enhancing interoperability of the application by designing an innovative tool able to enrich a given gem by linking it to relevant social media information. For such a purpose, we leverage on the enormous potential of Artificial Intelligence for cultural heritage (see for example the recent works by Fiorucci et al [10] and Díaz-Rodríguez and Pisoni [8]), and in particular, in this work we aim to better capture user attention by associating relevant keywords (tags) and YouTube videos (represented with proper thumbnails) to the gem. In particular, the system is able to select the videos that are most related to the given gem from the YouTube portal and extracts a set of meaningful thumbnails for each video.…”

Mediating distance: new interfaces and interaction design techniques to follow and take part in remote museum visits

“…To our knowledge, there has been no prior research that specifically tests the use of the drama-based approach for older adults in a remote museum visitation. Previous work focused on other types of approaches for remote museum visitations for older adults (Kostoska et al , 2015; Beer and Takayama, 2011; Kostoska et al , 2016; Pisoni et al , 2019; Díaz-Rodríguez and Pisoni, 2020), and our work advances the state of art by providing an empirical investigation of the appropriateness of the drama-based approach for remote museum visits for older adults. Our work addresses the need of this population to stay in contact with both people and places.…”

A new Italian Cultural Heritage data set: detecting fake reviews with BERT and ELECTRA leveraging the sentiment

“…In this sense, the exploitation of artificial intelligence techniques leaves ample room for improvement [2], [3]. In particular, the field of Natural Language Processing (NLP) can help to distinguish genuine reviews from fake ones by correctly directing efforts to modernize and improve the services offered for cultural heritage.…”