A Capabilities Approach to Studying Bias and Harm in Language Technologies

• URL: http://arxiv.org/abs/2411.04298v1
• Date: Wed, 06 Nov 2024 22:46:13 GMT
• Title: A Capabilities Approach to Studying Bias and Harm in Language Technologies
• Authors: Hellina Hailu Nigatu, Zeerak Talat,
• Abstract summary: We consider fairness, bias, and inclusion in Language Technologies through the lens of the Capabilities Approach. The Capabilities Approach centers on what people are capable of achieving, given their intersectional social, political, and economic contexts. We detail the Capabilities Approach, its relationship to multilingual and multicultural evaluation, and how the framework affords meaningful collaboration with community members in defining and measuring the harms of Language Technologies.
• Score: 4.135516576952934
• License:
• Abstract: Mainstream Natural Language Processing (NLP) research has ignored the majority of the world's languages. In moving from excluding the majority of the world's languages to blindly adopting what we make for English, we first risk importing the same harms we have at best mitigated and at least measured for English. However, in evaluating and mitigating harms arising from adopting new technologies into such contexts, we often disregard (1) the actual community needs of Language Technologies, and (2) biases and fairness issues within the context of the communities. In this extended abstract, we consider fairness, bias, and inclusion in Language Technologies through the lens of the Capabilities Approach. The Capabilities Approach centers on what people are capable of achieving, given their intersectional social, political, and economic contexts instead of what resources are (theoretically) available to them. We detail the Capabilities Approach, its relationship to multilingual and multicultural evaluation, and how the framework affords meaningful collaboration with community members in defining and measuring the harms of Language Technologies.

Related papers

• Lens: Rethinking Multilingual Enhancement for Large Language Models [70.85065197789639]
  Lens is a novel approach to enhance multilingual capabilities of large language models (LLMs) It operates by manipulating the hidden representations within the language-agnostic and language-specific subspaces from top layers of LLMs. It achieves superior results with much fewer computational resources compared to existing post-training approaches.
  arXiv  Detail & Related papers  (2024-10-06T08:51:30Z)
• The Call for Socially Aware Language Technologies [94.6762219597438]
  We argue that many of these issues share a common core: a lack of awareness of the factors, context, and implications of the social environment in which NLP operates. We argue that substantial challenges remain for NLP to develop social awareness and that we are just at the beginning of a new era for the field.
  arXiv  Detail & Related papers  (2024-05-03T18:12:39Z)
• Layers of technology in pluriversal design. Decolonising language technology with the LiveLanguage initiative [9.063726739562227]
  This paper uses LiveLanguage, a lexical database, as an example to discuss and close the gap from pluriversal design theory to practice. The paper presents a model comprising of five layers of technological activity.
  arXiv  Detail & Related papers  (2024-05-02T23:52:39Z)
• Diversity and Language Technology: How Techno-Linguistic Bias Can Cause Epistemic Injustice [4.234367850767171]
  We show that many attempts produce flawed solutions that adhere to a hard-wired representational preference for certain languages. As we show through the paper, techno-linguistic bias can result in systems that can only express concepts that are part of the language and culture of dominant powers. We argue that at the root of this problem lies a systematic tendency of technology developer communities to apply a simplistic understanding of diversity.
  arXiv  Detail & Related papers  (2023-07-25T16:08:27Z)
• Towards Bridging the Digital Language Divide [4.234367850767171]
  multilingual language processing systems often exhibit a hardwired, yet usually involuntary and hidden representational preference towards certain languages. We show that biased technology is often the result of research and development methodologies that do not do justice to the complexity of the languages being represented. We present a new initiative that aims at reducing linguistic bias through both technological design and methodology.
  arXiv  Detail & Related papers  (2023-07-25T10:53:20Z)
• No Language Left Behind: Scaling Human-Centered Machine Translation [69.28110770760506]
  We create datasets and models aimed at narrowing the performance gap between low and high-resource languages. We propose multiple architectural and training improvements to counteract overfitting while training on thousands of tasks. Our model achieves an improvement of 44% BLEU relative to the previous state-of-the-art.
  arXiv  Detail & Related papers  (2022-07-11T07:33:36Z)
• Evaluating the Diversity, Equity and Inclusion of NLP Technology: A Case Study for Indian Languages [35.86100962711644]
  In order for NLP technology to be widely applicable, fair, and useful, it needs to serve a diverse set of speakers across the world's languages. We propose an evaluation paradigm that assesses NLP technologies across all three dimensions.
  arXiv  Detail & Related papers  (2022-05-25T11:38:04Z)
• Not always about you: Prioritizing community needs when developing endangered language technology [5.670857685983896]
  We discuss the unique technological, cultural, practical, and ethical challenges that researchers and indigenous speech community members face. We report the perspectives of language teachers, Master Speakers and elders from indigenous communities, as well as the point of view of academics.
  arXiv  Detail & Related papers  (2022-04-12T05:59:39Z)
• Systematic Inequalities in Language Technology Performance across the World's Languages [94.65681336393425]
  We introduce a framework for estimating the global utility of language technologies. Our analyses involve the field at large, but also more in-depth studies on both user-facing technologies and more linguistic NLP tasks.
  arXiv  Detail & Related papers  (2021-10-13T14:03:07Z)
• AM2iCo: Evaluating Word Meaning in Context across Low-ResourceLanguages with Adversarial Examples [51.048234591165155]
  We present AM2iCo, Adversarial and Multilingual Meaning in Context. It aims to faithfully assess the ability of state-of-the-art (SotA) representation models to understand the identity of word meaning in cross-lingual contexts. Results reveal that current SotA pretrained encoders substantially lag behind human performance.
  arXiv  Detail & Related papers  (2021-04-17T20:23:45Z)
• Experience Grounds Language [185.73483760454454]
  Language understanding research is held back by a failure to relate language to the physical world it describes and to the social interactions it facilitates. Despite the incredible effectiveness of language processing models to tackle tasks after being trained on text alone, successful linguistic communication relies on a shared experience of the world.
  arXiv  Detail & Related papers  (2020-04-21T16:56:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.