Tracing Antisemitic Language Through Diachronic Embedding Projections: France 1789-1914

Tripodi, Rocco; Warglien, Massimo; Sullam, Simon Levis; Paci, Deborah

doi:10.48550/arxiv.1906.01440

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Again, these reconstructions are guided by insights into the topology and multi-scale network structures of these systems, including a set of possible transformation rules [50] . While the historical reconstruction of biological systems is based on material evidence (fossils) or models reconstructed from present-day DNA sequences, generalized interaction rules (functional network topologies) and patterns of transformation (developmental and evolutionary principles), an additional source of information in human history are text-based archives.…”

Section: Dynamics Of Multi-scale Networkmentioning

confidence: 99%

Computational History: Challenges and Opportunities of Formal Approaches

Jost,

Lalli,

Laubichler

et al. 2023

J. Soc. Comput.

View full text Add to dashboard Cite

We propose a program for a computational analysis, based on large scale datasets, of deep conceptual and formal structures, representing the mechanisms of historical transformations in different domains ranging from biological to social, cultural, and knowledge systems. We conceptualize such systems as consisting of complex multi-layer networks. Structural properties of such networks may explain the spreading of innovations. Temporal relations between the dynamics of interacting networks may help to identify causalities. Complex systems may show path and context dependencies. We illustrate our approach by case studies from all those types of systems.

show abstract

Section: Dynamics Of Multi-scale Networkmentioning

confidence: 99%

Computational History: Challenges and Opportunities of Formal Approaches

Jost,

Lalli,

Laubichler

et al. 2023

J. Soc. Comput.

View full text Add to dashboard Cite

show abstract

“…Recently, pre-trained language models (PLMs), e.g., BERT (Devlin et al, 2019), RoBERTa (Liu et al, 2019), GPT-2 (Radford et al, 2019) and DialoGPT (Zhang et al, 2020) have been shown to encode and amplify a range of stereotypical biases, such as racism, and sexism (e.g., Kurita et al, 2019a;Dev et al, 2020;Nangia et al, 2020;Lauscher et al, 2021a, inter alia). While such types of biases provide the basis for interesting academic research, e.g., historical analyses (e.g., Garg et al, 2018;Tripodi et al, 2019;Walter et al, 2021, inter alia), stereotyping constitutes a representational harm (Barocas et al, 2017;Blodgett et al, 2020), and can lead in many concrete socio-technical application scenarios to severe ethical issues by reinforcing societal biases (Hovy and Spruit, 2016;Shah et al, 2020;Mehrabi et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Fair and Argumentative Language Modeling for Computational Argumentation

Holtermann¹,

Lauscher²,

Ponzetto³

2022

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Although much work in NLP has focused on measuring and mitigating stereotypical bias in semantic spaces, research addressing bias in computational argumentation is still in its infancy. In this paper, we address this research gap and conduct a thorough investigation of bias in argumentative language models. To this end, we introduce AB BA , a novel resource for bias measurement specifically tailored to argumentation. We employ our resource to assess the effect of argumentative fine-tuning and debiasing on the intrinsic bias found in transformer-based language models using a lightweight adapter-based approach that is more sustainable and parameterefficient than full fine-tuning. Finally, we analyze the potential impact of language model debiasing on the performance in argument quality prediction, a downstream task of computational argumentation. Our results show that we are able to successfully and sustainably remove bias in general and argumentative language models while preserving (and sometimes improving) model performance in downstream tasks. We make all experimental code and data available at https://github.com/ umanlp/FairArgumentativeLM.

show abstract

Tracing Antisemitic Language Through Diachronic Embedding Projections: France 1789-1914

Cited by 2 publications

References 0 publications

Computational History: Challenges and Opportunities of Formal Approaches

Computational History: Challenges and Opportunities of Formal Approaches

Fair and Argumentative Language Modeling for Computational Argumentation

Contact Info

Product

Resources

About