Queens are powerful too: Mitigating gender bias in dialogue generation
Models often easily learn biases present in the training data, and their predictions directly
reflect this bias. We analyze gender bias in dialogue data, and examine how this bias is …
reflect this bias. We analyze gender bias in dialogue data, and examine how this bias is …
Theories of “gender” in nlp bias research
H Devinney, J Björklund, H Björklund - … of the 2022 ACM conference on …, 2022 - dl.acm.org
The rise of concern around Natural Language Processing (NLP) technologies containing
and perpetuating social biases has led to a rich and rapidly growing area of research …
and perpetuating social biases has led to a rich and rapidly growing area of research …
Gender Bias in Natural Language Processing and Computer Vision: A Comparative Survey
Taking an interdisciplinary approach to surveying issues around gender bias in textual and
visual AI, we present literature on gender bias detection and mitigation in NLP, CV, as well …
visual AI, we present literature on gender bias detection and mitigation in NLP, CV, as well …
Adhering, steering, and queering: Treatment of gender in natural language generation
Natural Language Generation (NLG) supports the creation of personalized, contextualized,
and targeted content. However, the algorithms underpinning NLG have come under scrutiny …
and targeted content. However, the algorithms underpinning NLG have come under scrutiny …
Sociolinguistically driven approaches for just natural language processing
SL Blodgett - 2021 - scholarworks.umass.edu
Natural language processing (NLP) systems are now ubiquitous. Yet the benefits of these
language technologies do not accrue evenly to all users, and indeed they can be harmful; …
language technologies do not accrue evenly to all users, and indeed they can be harmful; …
Large language models shape and are shaped by society: A survey of arxiv publication patterns
There has been a steep recent increase in the number of large language model (LLM)
papers, producing a dramatic shift in the scientific landscape which remains largely …
papers, producing a dramatic shift in the scientific landscape which remains largely …
Measuring societal biases from text corpora with smoothed first-order co-occurrence
Text corpora are widely used resources for measuring societal biases and stereotypes. The
common approach to measuring such biases using a corpus is by calculating the similarities …
common approach to measuring such biases using a corpus is by calculating the similarities …
What do users care about? detecting actionable insights from user feedback
K Bhattacharjee, R Gangadharaiah… - Proceedings of the …, 2022 - aclanthology.org
Users often leave feedback on a myriad of aspects of a product which, if leveraged
successfully, can help yield useful insights that can lead to further improvements down the …
successfully, can help yield useful insights that can lead to further improvements down the …
Gender and representation: investigations of bias in natural language processing
H Devinney - 2024 - diva-portal.org
Abstract Natural Language Processing (NLP) technologies are a part of our every day
realities. They come in forms we can easily see as 'language technologies'(autocorrect …
realities. They come in forms we can easily see as 'language technologies'(autocorrect …
Detecting objectifying language in online professor reviews
Student reviews often make reference to professors' physical appearances. Until recently
RateMyProfessors. com, the website of this study's focus, used a design feature to …
RateMyProfessors. com, the website of this study's focus, used a design feature to …