"Thy algorithm shalt not bear false witness": An Evaluation of Multiclass Debiasing Methods on Word Embeddings

• URL: http://arxiv.org/abs/2010.16228v2
• Date: Wed, 4 Nov 2020 09:24:21 GMT
• Title: "Thy algorithm shalt not bear false witness": An Evaluation of Multiclass Debiasing Methods on Word Embeddings
• Authors: Thalea Schlender and Gerasimos Spanakis
• Abstract summary: The paper investigates the state-of-the-art multiclass debiasing techniques: Hard debiasing, SoftWEAT debiasing and Conceptor debiasing. It evaluates their performance when removing religious bias on a common basis by quantifying bias removal via the Word Embedding Association Test (WEAT), Mean Average Cosine Similarity (MAC) and the Relative Negative Sentiment Bias (RNSB)
• Score: 3.0204693431381515
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the vast development and employment of artificial intelligence applications, research into the fairness of these algorithms has been increased. Specifically, in the natural language processing domain, it has been shown that social biases persist in word embeddings and are thus in danger of amplifying these biases when used. As an example of social bias, religious biases are shown to persist in word embeddings and the need for its removal is highlighted. This paper investigates the state-of-the-art multiclass debiasing techniques: Hard debiasing, SoftWEAT debiasing and Conceptor debiasing. It evaluates their performance when removing religious bias on a common basis by quantifying bias removal via the Word Embedding Association Test (WEAT), Mean Average Cosine Similarity (MAC) and the Relative Negative Sentiment Bias (RNSB). By investigating the religious bias removal on three widely used word embeddings, namely: Word2Vec, GloVe, and ConceptNet, it is shown that the preferred method is ConceptorDebiasing. Specifically, this technique manages to decrease the measured religious bias on average by 82,42%, 96,78% and 54,76% for the three word embedding sets respectively.

Related papers

• Mitigating Gender Bias in Contextual Word Embeddings [1.208453901299241]
  We propose a novel objective function for Lipstick(Masked-Language Modeling) which largely mitigates the gender bias in contextual embeddings. We also propose new methods for debiasing static embeddings and provide empirical proof via extensive analysis and experiments.
  arXiv  Detail & Related papers  (2024-11-18T21:36:44Z)
• Debiasing Sentence Embedders through Contrastive Word Pairs [46.9044612783003]
  We explore an approach to remove linear and nonlinear bias information for NLP solutions. We compare our approach to common debiasing methods on classical bias metrics and on bias metrics which take nonlinear information into account.
  arXiv  Detail & Related papers  (2024-03-27T13:34:59Z)
• What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations [62.91799637259657]
  Do large language models (LLMs) exhibit sociodemographic biases, even when they decline to respond? We study this research question by probing contextualized embeddings and exploring whether this bias is encoded in its latent representations. We propose a logistic Bradley-Terry probe which predicts word pair preferences of LLMs from the words' hidden vectors.
  arXiv  Detail & Related papers  (2023-11-30T18:53:13Z)
• The SAME score: Improved cosine based bias score for word embeddings [49.75878234192369]
  We introduce SAME, a novel bias score for semantic bias in embeddings. We show that SAME is capable of measuring semantic bias and identify potential causes for social bias in downstream tasks.
  arXiv  Detail & Related papers  (2022-03-28T09:28:13Z)
• Identification of Biased Terms in News Articles by Comparison of Outlet-specific Word Embeddings [9.379650501033465]
  We train two word embedding models, one on texts of left-wing, the other on right-wing news outlets. Our hypothesis is that a word's representations in both word embedding spaces are more similar for non-biased words than biased words. This paper presents the first in-depth look at the context of bias words measured by word embeddings.
  arXiv  Detail & Related papers  (2021-12-14T13:23:49Z)
• Balancing out Bias: Achieving Fairness Through Training Reweighting [58.201275105195485]
  Bias in natural language processing arises from models learning characteristics of the author such as gender and race. Existing methods for mitigating and measuring bias do not directly account for correlations between author demographics and linguistic variables. This paper introduces a very simple but highly effective method for countering bias using instance reweighting.
  arXiv  Detail & Related papers  (2021-09-16T23:40:28Z)
• Towards Debiasing Sentence Representations [109.70181221796469]
  We show that Sent-Debias is effective in removing biases, and at the same time, preserves performance on sentence-level downstream tasks. We hope that our work will inspire future research on characterizing and removing social biases from widely adopted sentence representations for fairer NLP.
  arXiv  Detail & Related papers  (2020-07-16T04:22:30Z)
• Nurse is Closer to Woman than Surgeon? Mitigating Gender-Biased Proximities in Word Embeddings [37.65897382453336]
  Existing post-processing methods for debiasing word embeddings are unable to mitigate gender bias hidden in the spatial arrangement of word vectors. We propose RAN-Debias, a novel gender debiasing methodology which eliminates the bias present in a word vector but also alters the spatial distribution of its neighbouring vectors. We also propose a new bias evaluation metric - Gender-based Illicit Proximity Estimate (GIPE)
  arXiv  Detail & Related papers  (2020-06-02T20:50:43Z)
• Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation [94.98656228690233]
  We propose a technique that purifies the word embeddings against corpus regularities prior to inferring and removing the gender subspace. Our approach preserves the distributional semantics of the pre-trained word embeddings while reducing gender bias to a significantly larger degree than prior approaches.
  arXiv  Detail & Related papers  (2020-05-03T02:33:20Z)
• Joint Multiclass Debiasing of Word Embeddings [5.1135133995376085]
  We present a joint multiclass debiasing approach capable of debiasing multiple bias dimensions simultaneously. We show that our concepts can both reduce or even completely eliminate bias, while maintaining meaningful relationships between vectors in word embeddings.
  arXiv  Detail & Related papers  (2020-03-09T22:06:37Z)

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.