115 research outputs found
The Battle for the Piazza: Creative Antagonism between Itinerant Preachers and Street Singers in Late Medieval and Early Modern Italy
No full textThis book studies the uses of orality in Italian society, across all classes, from the fifteenth to the seventeenth century, with an emphasis on the interrelationships between oral communication and the written word. The Introduction provides an overview of the topic as a whole and links the chapters together. Part 1 concerns public life in the states of northern, central, and southern Italy. The chapters examine a range of performances that used the spoken word or song: concerted shouts that expressed the feelings of the lower classes and were then recorded in writing; the proclamation of state policy by town criers; songs that gave news of executions; the exercise of power relations in society as recorded in trial records; and diplomatic orations and interactions. Part 2 centres on private entertainments. It considers the practices of the performance of poetry sung in social gatherings and on stage with and without improvisation; the extent to which lyric poets anticipated the singing of their verse and collaborated with composers; performances of comedies given as dinner entertainments for the governing body of republican Florence; and a reading of a prose work in a house in Venice, subsequently made famous through a printed account. Part 3 concerns collective religious practices. Its chapters study sermons in their own right and in relation to written texts, the battle to control spaces for public performance by civic and religious authorities, and singing texts in sacred spaces
Manually annotated song lyrics dataset with fine-grained explicitness information
No full textWe contribute a new dataset of English song lyrics, manually annotated with detailed information on the reasons for the explicitness (if any) of their content: Strong language; Substance abuse; Sexual reference; Reference to violence; Discriminatory language. The dataset consists of 4000 song lyrics, 1707 of them annotated as explicit and 2293 annotated as non-explicit by the human annotators. In details, the annotators tagged the explicit song lyrics as follows: 926 lyrics with Strong language; 266 lyrics with Substance abuse; 398 lyrics with Sexual reference; 771 lyrics with Reference to violence; and, 147 lyrics with Discriminatory language. The construction of the dataset is described in the following associated publication: Rospocher, M.; Eksir, S. Assessing Fine-Grained Explicitness of Song Lyrics. Information 2023, 14, 159. https://doi.org/10.3390/info1403015
Introduction : migration and the European City
No full textLooking back over the centuries, mobility and migration have always formed an important part of human existence. Given the multiplicity of push/pull factors and shifting constellations, the groups as well as trajectories involved in the movement of people can vary dramatically. It is worth remembering, for example, that regions like Europe – perceived as a preferred destination in the twenty-first century – provided large numbers of emigrants in the past, particularly during the high medieval crusades or global expansion and colonialization between the fifteenth and nineteenth centuries. In numbers, however, the migration of labor was to outweigh these groups by far; roughly, 60 million Europeans crossed the Atlantic to the Americas during the long nineteenth century in search of a new place of work
SPKS: Surgical Procedural Knowledge Sentences dataset
No full textSPKS is a textual dataset of the surgical robotic field consisting of 1958 sentences (37022 words and 3999 unique words) manually annotated as procedural and non-procedural by an expert annotator. To the best of our knowledge, SPKS is the first dataset in the literature containing procedural annotated sentences from the surgical robotic sector. We believe it is an indispensable resource for anyone who wants to test their classification algorithms in order to detect procedural knowledge in surgical written texts. The sentences are taken from different sources, and cover various robotic surgery procedures in urology, gynecology, gastrointestinal procedures, and thoracic procedures. The construction of the dataset is described in the following associated publication (c.f. Sections "Dataset" and "Preprocessing the dataset"): Bombieri, M., Rospocher, M., Dall’Alba, D., Fiorini, P. Automatic detection of procedural knowledge in robotic-assisted surgical texts. International Journal of Computer Assisted Radiology and Surgery (2021). DOI: 10.1007/s11548-021-02370-
On exploiting transformers for detecting explicit song lyrics
No full textDetermining if the lyrics of a given song could be hurtful or inappropriate for children is of utmost importance to prevent the reproduction of songs whose textual content is unsuitable for them. This problem can be computationally tackled as a binary classification task, and in the last couple of years various machine learning approaches have been applied to perform this task automatically. In this work, we investigate the automatic detection of explicit song lyrics by leveraging transformer-based language models, i.e., large language representations, unsupervisely built from huge textual corpora, that can be fine-tuned on various natural language processing tasks, such as text classification. We assess the performance of various transformer-based language model classifiers on a dataset consisting of more than 800K lyrics, marked with explicit information. The evaluation shows that while the classifiers built with these powerful tools achieve state-of-the-art performance, they do not outperform lighter and computationally less demanding approaches. We complement this empirical evaluation with further analyses, including an assessment of the performance of these classifiers in a few-shot learning scenario, where they are trained with just few thousands of samples
Explicit song lyrics detection with subword-enriched word embeddings
No full textIn this paper, we investigate the problem of automatically detecting explicit song lyrics, i.e., determining if the lyrics of a given song could be offensive or unsuitable for children. The problem can be framed as a binary classification task, and in this work we propose to tackle it with the FASTTEXT classifier, an efficient linear classification model leveraging a peculiar distributional text representation that, by exploiting subword information in building the embeddings of the words, enables to cope with words not seen at training time. We assess the performance of the FASTTEXT classifier and word representations with a lyrics dataset of over 800K songs, annotated with explicit information, that we assembled from publicly available resources. The evaluation shows that the FASTTEXT classifier is effective for explicit lyrics detection, substantially outperforming a reference approach for the task, and that the subword information effectively contributes to this result. (C) 2020 Elsevier Ltd. All rights reserved
Editorial Message: Special track on cognitive computing
No full texteditorial of the Special track on Cognitive Computin
- …
