• Digital Humanities and Cultural Heritage
• Other ORP type close
• CH close

The site of La Roche-à-Pierrot in Saint-Césaire (Charente-Maritime, France) produced a succession of Mousterian, Châtelperronian and Aurignacian occupations, and continues to play a central role in debates concerning the Middle-to-Upper Palaeolithic transition. The source of controversy surrounding the site relates to ambiguities concerning the overall archaeological sequence, the cultural association of the human remains found at the site and the limited number of robust absolute dates. Here, we present the results of a multiscalar, multiproxy geoarchaeological investigation of the site's sedimentary sequence. Our study integrates geomorphology, field lithostratigraphy, microstratigraphy, geochemistry and absolute dating methods (radiocarbon and optically stimulated luminescence) designed to characterize site formation processes. We propose a site formation model involving the evolution of a karstified limestone cliff from a semi-closed system to an exposed slope deposit, with sediments at the base of the cliff accumulating under periglacial conditions of MIS3, broadly between ca. 59.9 ± 3.9 ka and ca. 37.7 ka. The lowermost Mousterian occupations took place in a semi-closed, sheltered space in which sedimentary rates were low, involving mainly cryoclastic roof spall and episodic percolation of fine-grained sediment. This depositional environment generated a Mousterian archaeological palimpsest in the proximal area and translocated downslope. Subsequent Mousterian, Châtelperronian and Aurignacian remains embedded within diamictons were deposited in an open-air context, on a sloping surface at the apex of a palaeotalus, and possibly above the site, at the top of the cliff. The resulting diachronous surfaces and immature deposits were subject to solifluction and slopewash, with low sedimentary rates. Our geoarchaeological study sheds new light on previously noted spatial inconsistencies in the archaeological sequence and constitutes a rigorous framework for further archaeological research at the site, highlighting the potential of a multiscalar, multiproxy site formation research to improve stratigraphic investigation of Palaeolithic sites in similar geomorphological contexts.

Hard-of-hearing people face challenges in daily interactions that involve spoken language, such as meetings or doctor’s visits. Automatic speech recognition technology can support them by providing a written transcript of the conversation. Pro Audito Schweiz, the Swiss federation of hard-of-hearing people, and the Centre for Artificial Intelligence (CAI) at the Zurich University of Applied Sciences (ZHAW) conducted a preliminary study into the use of Speech-to-Text (STT) for this target group. Our survey among the members of Pro Audito found that there is large interest in using automated solutions for better understanding in everyday situations. We now propose to take the next step and develop an application which uses ZHAW’s high-quality STT models.

Non-destructive dendrochronology plays an important role in the dating of outstanding archaeological objects. A prerequisite for successful dating of an object based on X-ray computed tomography (CT) is the quality of the measurement data, which is mainly influenced by the conservation method. The aim of this research was to investigate to what extent the methods alcohol-ether-resin, melamine formaldehyde (Kauramin 800) and polyethylene glycol (PEG) 2000 with freeze-drying influencethe visibility of the annual rings. For this purpose, conserved samples of pine and oak wood, respectively, were measured by laboratory-based X-ray micro-computed tomography (µCT) and the contrast in the data was compared. In addition, the structure was measured by synchrotron µCT. The investigations showed that the alcohol-ether-resin as well as the melamine formaldehyde conservation methods stabilise the cell wall. In contrast, PEG is deposited to a certain extent in the cell lumen, which reduces the contrast and thus renders measuring the tree-ring width more challenging. 

This research was funded by the Swiss National Science Foundation’s Digital Lives Scheme (Grant project 10DL15_183194) and the Swiss National Science Foundation’s Eccellenza scheme (Grant project PCEFP1_203293).

Digital skills can be a valuable resource in work life, especially in such times as the current COVID-19 pandemic, during which working from home has become new reality. Although increasing numbers of older employees (aged 50 years and above) are using digital technologies to work remotely, many of these older adults still have generally lower digital skills. Whether the pandemic will be a push factor for the acquisition of computer skills in late working life remains unclear. This study investigated the explanatory factors of the computer skills gained by older workers who were working from home during the COVID-19 pandemic, using representative data for 28 countries from the Survey of Health, Aging and Retirement in Europe (SHARE). The analysis of the survey responses of 11,042 employed persons aged 50 years and older revealed that, 13% worked only at home due to the pandemic, while 15% said they worked at home and in their usual workplace. The descriptives indicate that full-time homeworking is more of an option among those with tertiary education and who already have some computer skills. Of the older employees who worked only at home, 36% reported an improvement in their computer skills, whereas of the older workers who worked at home and at their usual workplaces, only 29% reported such an improvement. Our results based on logistic regressions suggest that significantly more women, younger employees, respondents with tertiary educational qualifications, and those whose work was not affected by unemployment or even business closure acquired new computer skills, regardless of whether they were working permanently or only partly from home. The study underlines the importance of investigating the possible digital skills gained from the home office situation resulting from the pandemic.

This paper presents the contribution of ZHAW-CAI to the Shared Task ”Swiss German Speech to Standard German Text” at the SwissText 2021 conference. Our approach combines three models based on the Fairseq, Jasper and Wav2vec architectures trained on multilingual, German and Swiss German data. We applied an ensembling algorithm on the predictions of the three models in order to retrieve the most reliable candidate out of the provided translations for each spoken utterance. With the ensembling output, we achieved a BLEU score of 39.39 on the private test set, which gave us the third place out of four contributors in the competition.

Dialogue summarization is a long-standing task in the field of NLP, and several data sets with dialogues and associated human-written summaries of different styles exist. However, it is unclear for which type of dialogue which type of summary is most appropriate. For this reason, we apply a linguistic model of dialogue types to derive matching summary items and NLP tasks. This allows us to map existing dialogue summarization data sets into this model and identify gaps and potential directions for future work. As part of this process, we also provide an extensive overview of existing dialogue summarization data sets.

Ice core dating is the first step for a correct interpretation of climatic and environmental changes. In this work, we release the dating of the uppermost 197 m of the 250 m deep GV7(B) ice core (drill site, 70∘41′ S, 158∘52′ E; 1950 m a.s.l. in Oates Land, East Antarctica) with a sub-annual resolution. Chemical records of NO3-, MSA (methanesulfonic acid), non-sea-salt SO42- (nssSO42-), sea-salt ions and water stable isotopes (δ18O) were studied as candidates for dating due to their seasonal pattern. Different procedures were tested but the nssSO42- record proved to be the most reliable on the short- and long-term scales, so it was chosen for annual layer counting along the whole ice core. The dating was constrained by using volcanic signatures from historically known events as tie points, thus providing an accurate age–depth relationship for the period 1179–2009 CE. The achievement of the complete age scale allowed us to calculate the annual mean accumulation rate throughout the analyzed 197 m of the core, yielding an annually resolved history of the snow accumulation on site in the last millennium. A small yet consistent rise in accumulation rate (Tr = 1.6, p<0.001) was found for the last 830 years starting around mid-18th century.

SwissText is an annual conference that brings together text analytics experts from industry and academia. It is organised by the Swiss Association for Natural Language Processing (SwissNLP) in collaboration with the University of Applied Sciences and Arts Northwestern Switzerland (FHNW) as well as the Zurich University of Applied Sciences (ZHAW) and the data innovation alliance. SwissText 2021 was part of the Networking Event Series – Natural Language Processing funded by InnoSuisse, the Swiss Innovation Agency. It is supported by more than 10 universities and scientific associations.