• Digital Humanities and Cultural Heritage
• 2021-2021close
• Publications close
• Other research products close
• CHIST-ERA close
• Digital Humanities and Cultural Her... close

Can we rethink the paradigms that have guided our observation, participation and relationships with nature to date through artistic practice and art-inspired thinking and by increasing the use of new technologies? Since time immemorial, the human body has coalesced, entangled, and co-evolved with nature. One of the very first relationships we ever formed, as humans on Earth, was the one we had—and continue to have—with plants. Yet more often than not, in this modern world, when we think seriously of communing meaningfully with nature, of actual plant-human and more-than human relationships, we are met with a reductionist worldview, where nature is generally seen as a non-agential, non-sentient, backdrop to the central drama of human life on Earth. Gilles Clément1 envisioned our world as a “planetary garden,” collapsing the anthropocentric divisions of good and bad, and intentionally collaborating with rather than “managing” plants and all other nonhuman living beings. Our initiative, Our Planetary Garden, we seek to foster alliances of technology and artistic practice to explore possible ways to address our relationship with the environment: ranging from aesthetic, multi-sensorial, associative, affective, spatial and visual modes of ‘knowledge’ to more discursive, analytical, contextualised ones. Our Planetary Garden proposes two art-practice engagements with the Ministry and the Biodiversity Monitoring Project, where in the following 6-months our team, exploration space, will develop (2) artworks based on two main databases provided by the Biodiversity Monitoring Project. Our work outputs will provide the farmers and community new angles and sensory aspects to consider and experience as stewards of the land, and how to grow liveable worlds. Moreover, these engagements present the concept of “planetary” where Everything is conscious in our environment and thus capable of reciprocal relationships. Communicating, flourishing, and making kin with plants then becomes not only possible, but embedded as a feature of normal awareness as well as ritualized practice. Through nature, we are therefore entangled with an invisible thread that connects all that is living, because, quite simply, we are alive and co-evolve in a shared space. When we attune our human senses to the vibrancy of life itself, it is impossible not to feel a sense of mystery and reverence pulsating through all bodies of ecology. 

The Arabic language has many varieties, including its standard form, Modern Standard Arabic (MSA), and its spoken forms, namely the dialects. Those dialects are representative examples of under-resourced languages for which automatic speech recognition is considered as an unresolved issue. To address this issue, we recorded several hours of spoken Algerian dialect and used them to train a baseline model. This model was boosted afterwards by taking advantage of other languages that impact this dialect by integrating their data in one large corpus and by investigating three approaches: multilingual training, multitask learning and transfer learning. The best performance was achieved using a limited and balanced amount of acoustic data from each additional language, as compared to the data size of the studied dialect. This approach led to an improvement of 3.8% in terms of word error rate in comparison to the baseline system trained only on the dialect data. International audience

Abstract We demonstrate improved performance in the classification of bioelectric data for use in systems such as robotic prosthesis control, by data fusion using low-cost electromyography (EMG) and electroencephalography (EEG) devices. Prosthetic limbs are typically controlled through EMG, and whilst there is a wealth of research into the use of EEG as part of a brain-computer interface (BCI) the cost of EEG equipment commonly prevents this approach from being adopted outside the lab. This study demonstrates as a proof-of-concept that multimodal classification can be achieved by using low-cost EMG and EEG devices in tandem, with statistical decision-level fusion, to a high degree of accuracy. We present multiple fusion methods, including those based on Jensen-Shannon divergence which had not previously been applied to this problem. We report accuracies of up to 99% when merging both signal modalities, improving on the best-case single-mode classification. We hence demonstrate the strengths of combining EMG and EEG in a multimodal classification system that could in future be leveraged as an alternative control mechanism for robotic prostheses.

Neural network architectures in natural language processing often use attention mechanisms to produce probability distributions over input token representations. Attention has empirically been demonstrated to improve performance in various tasks, while its weights have been extensively used as explanations for model predictions. Recent studies (Jain and Wallace, 2019; Serrano and Smith, 2019; Wiegreffe and Pinter, 2019) have showed that it cannot generally be considered as a faithful explanation (Jacovi and Goldberg, 2020) across encoders and tasks. In this paper, we seek to improve the faithfulness of attention-based explanations for text classification. We achieve this by proposing a new family of Task-Scaling (TaSc) mechanisms that learn task-specific non-contextualised information to scale the original attention weights. Evaluation tests for explanation faithfulness, show that the three proposed variants of TaSc improve attention-based explanations across two attention mechanisms, five encoders and five text classification datasets without sacrificing predictive performance. Finally, we demonstrate that TaSc consistently provides more faithful attention-based explanations compared to three widely-used interpretability techniques. NLP Interpretability ; Accepted at ACL2021