3,776 research outputs found
Helena Kolody, carbono & diamante: uma biografia ilustrada
No full textTese (doutorado) - Universidade Federal de Santa Catarina, Centro de Comunicação e Expressão. Programa de Pós-Graduação em LiteraturaHelena Kolody, carbono & diamante - uma biografia ilustrada conta a vida da escritora Helena Kolody, a partir de sua inscrição na literatura, questionando sua identidade, o mundo que a cercava e o sentido de sua existência. Equivale a dizer: em sua lírica, reflexões e sentimentos se entretecem a partir de uma matéria pessoal e localizada. Da estação ferroviária à estação tubo; da Ucrânia ao centro de Curitiba; de Paisagem interior a Reika; do século XIX ao século XXI, a literatura de Helena Kolody gerencia sua presença na consolidação do binômio arte-vida. O retrato da autora acaba se constituindo também por meio de farto aparato iconográfico; pelos mais de quinhentos textos críticos elencados e por sua obra completa. Fragmentação deliberadamente assumida, a pessoa se revela em sua inteireza.Helena Kolody, carbon & diamond - an illustrated biography tells the life of Helena Kolody, from her very insertion in literature, as it questions her identity, the world surrounding her, and the meaning of her existence. That is equivalent to saying that in her poetry there is the intermingling of reflections and feelings that derive from personal and localized material. From the railroad station to the tube-shaped bus stops; from Ukraine to downtown Curitiba; from Paisagem interior to Reika; from the nineteenth century to the twenty-first century, Helena Kolody's literature guarantees her presence in the consolidation of the art/life binomial. The portrait of the author ends up by also being made up of an abundant iconographic apparatus, of the over five hundred critical texts listed, and of her complete work. The person, although deliberately accepting her own fragmentation, reveals herself in her entireness
Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech
No full textUndermining the impact of hateful content with informed and non-aggressive responses, called counter narratives, has emerged as a possible solution for having healthier online communities. Thus, some NLP studies have started addressing the task of counter narrative generation. Although such studies have made an effort to build hate speech / counter narrative (HS/CN) datasets for neural generation, they fall short in reaching either high-quality and/or high-quantity. In this paper, we propose a novel human-in-the-loop data collection methodology in which a generative language model is refined iteratively by using its own data from the previous loops to generate new training samples that experts review and/or post-edit. Our experiments comprised several loops including diverse dynamic variations. Results show that the methodology is scalable and facilitates diverse, novel, and cost-effective data collection. To our knowledge, the resulting dataset is the only expert-based multi-target HS/CN dataset available to the community
Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering
No full textFighting online hate speech is a challenge that is usually addressed using
Natural Language Processing via automatic detection and removal of hate
content. Besides this approach, counter narratives have emerged as an effective
tool employed by NGOs to respond to online hate on social media platforms. For
this reason, Natural Language Generation is currently being studied as a way to
automatize counter narrative writing. However, the existing resources necessary
to train NLG models are limited to 2-turn interactions (a hate speech and a
counter narrative as response), while in real life, interactions can consist of
multiple turns. In this paper, we present a hybrid approach for dialogical data
collection, which combines the intervention of human expert annotators over
machine generated dialogues obtained using 19 different configurations. The
result of this work is DIALOCONAN, the first dataset comprising over 3000
fictitious multi-turn dialogues between a hater and an NGO operator, covering 6
targets of hate.Comment: To appear in Proceedings of the 2022 Conference on Empirical Methods
in Natural Language Processing (long paper
Transient observations : the textualizing of St Helena through five hundred years of colonial discourse
No full textThis thesis explores the textualizing of the South Atlantic island of St Helena (a
British Overseas Territory) through an analysis of the relationship between
colonizing practices and the changing representations of the island and its
inhabitants in a range of colonial 'texts', including historiography, travel writing,
government papers, creative writing, and the fine arts.
Part I situates this thesis within a critical engagement with post-colonial
theory and colonial discourse analysis primarily, as well as with the recent
'linguistic turn' in anthropology and history. In place of post-colonialism's rather
monolithic approach to colonial experiences, I argue for a localised approach to
colonisation, which takes greater account of colonial praxis and of the continuous
re-negotiation and re-constitution of particular colonial situations.
Part II focuses on a number of literary issues by reviewing St Helena's
historiography and literature, and by investigating the range of narrative tropes
employed (largely by travellers) in the textualizing of St Helena, in particular
with respect to recurrent imaginings of the island in terms of an earthly Eden.
Part III examines the nature of colonial 'possession' by tracing the island's
gradual appropriation by the Portuguese, Dutch and English in the sixteenth and
early seventeenth century and the settlement policies pursued by the English
East India Company in the late seventeenth and early eighteenth century.
Part IV provides an account of the changing perceptions, by visitors and
colonial officials alike, of the character of the island's inhabitants (from the late
eighteenth to the early twentieth century) and assesses the influence that these
perceptions have had on the administration of the island and the political status of
its inhabitants (in the mid- to late twentieth century).
Part V, the conclusion, reviews the principal arguments of my thesis by
addressing the political implications of post-colonial theory and of my own
research, while also indicating avenues for further research.
A localised and detailed exploration of colonial discourse over a period of
nearly five hundred years, and a close analysis of a consequently wide range of
colonial 'texts', has confirmed that although colonising practices and
representations are far from monolithic, in the case of St Helena their continuities
are of as much significance as their discontinuities
Weigh your own words: improving hate speech counter narrative generation via attention regularization
No full textUsing Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study
No full textIn this work, we present an extensive study on the use of pre-trained language models for the task of automatic Counter Narrative (CN) generation to fight online hate speech in English. We first present a comparative study to determine whether there is a particular Language Model (or class of LMs) and a particular decoding mechanism that are the most appropriate to generate CNs. Findings show that autoregressive models combined with stochastic decodings are the most promising. We then investigate how an LM performs in generating a CN with regard to an unseen target of hate. We find out that a key element for successful ‘out of target’ experiments is not an overall similarity with the training data but the presence of a specific subset of training data, i. e. a target that shares some commonalities with the test target that can be defined a-priori. We finally introduce the idea of a pipeline based on the addition of an automatic post-editing step to refine generated CNs
NLP for Counterspeech against Hate: A Survey and How-To Guide
No full textIn recent years, counterspeech has emerged as one of the most promising strategies to fight online hate. These non-escalatory responses tackle online abuse while preserving the freedom of speech of the users, and can have a tangible impact in reducing online and offline violence. Recently, there has been growing interest from the Natural Language Processing (NLP) community in addressing the challenges of analysing, collecting, classifying, and automatically generating counterspeech, to reduce the huge burden of manually producing it. In particular, researchers have taken different directions in addressing these challenges, thus providing a variety of related tasks and resources. In this paper, we provide a guide for doing research on counterspeech, by describing - with detailed examples - the steps to undertake, and providing best practices that can be learnt from the NLP studies on this topic. Finally, we discuss open challenges and future directions of counterspeech research in NLP
Weigh Your Own Words: Improving Hate Speech Counter Narrative Generation via Attention Regularization
No full textRecent computational approaches for combating online hate speech involve the automatic generation of counter narratives by adapting Pretrained Transformer-based Language Models (PLMs) with human-curated data. This process, however, can produce in-domain overfitting, resulting in models generating acceptable narratives only for hatred similar to training data, with little portability to other targets or to real-world toxic language. This paper introduces novel attention regularization methodologies to improve the generalization capabilities of PLMs for counter narratives generation. Overfitting to training-specific terms is then discouraged, resulting in more diverse and richer narratives. We experiment with two attention-based regularization techniques on a benchmark English dataset. Regularized models produce better counter narratives than state-of-the-art approaches in most cases, both in terms of automatic metrics and human evaluation, especially when hateful targets are not present in the training data. This work paves the way for better and more flexible counter-speech generation models, a task for which datasets are highly challenging to produce
Helena Więckowska’s activity as a director of the Library of the Łódź University
No full textProfesor Helena Więckowska (1897–1984) była z pewnością jedną z najbardziej znaczących postaci w polskim bibliotekarstwie, w okresie powojennym. Wniosła także istotny wkład w rozwój polskiej bibliologii i wydatnie przyczyniła się do ukształtowania systemu akademickiego kształcenia bibliotekarzy. Bibliografia Jej dorobku naukowego liczy 221 pozycji. Są w nim rozprawy, artykuły, recenzje, hasła w słownikach i encyklopediach. Jest to również dorobek zróżnicowany tematycznie, co potwierdza trafność określenia „bibliolog praktyk”, użytego wobec dokonań Profesor Więckowskiej przez Krzysztofa Migonia.The author of the article discusses the activities of Helena Więckowska – the second in the order director of the Library of the Łódź University. In the text you can find information about the problems that she as a director had to face: first of all with the facilities but also with the development of collections. The author mentiones that Helena Więckowska cared very much about the vocational training of employees: improving the librarians’ qualifications, gaining degrees. In 1954 she decided to train students in the field of using the library. She retired in 1969 – after 21 years as a director of the university’s library.Publikacja współfinansowana przez Bibliotekę UŁ oraz Wydział Filologiczny UŁ
Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering
No full textThe potential effectiveness of counterspeech as a hate speech mitigation strategy is attracting increasing interest in the NLG research community, particularly towards the task of automatically producing it. However, automatically generated responses often lack the argumentative richness which characterises expert-produced counterspeech. In this work, we focus on two aspects of counterspeech generation to produce more cogent responses. First, by investigating the tension between helpfulness and harmlessness of LLMs, we test whether the presence of safety guardrails hinders the quality of the generations. Secondly, we assess whether attacking a specific component of the hate speech results in a more effective argumentative strategy to fight online hate. By conducting an extensive human and automatic evaluation, we show how the presence of safety guardrails can be detrimental also to a task that inherently aims at fostering positive social interactions. Moreover, our results show that attacking a specific component of the hate speech, and in particular its implicit negative stereotype and its hateful parts, leads to higher-quality generations
- …
