paper-with-me

Papers

On Measuring and Mitigating Biased Inferences of Word Embeddings

2019-08-25 · Sunipa Dev, Tao Li, Jeff Phillips, Vivek Srikumar

Word embeddings carry stereotypical connotations from the text they are trained on, which can lead to invalid inferences in downstream models that rely on them. We use this observation to design a mechanism for measuring stereotypes using the task of natural language inference. We demonstrate a reduction in invalid inferences via bias mitigation strategies on static word embeddings (GloVe). Further, we show that for gender bias, these techniques extend to contextualized embeddings when applied selectively only to the static components of contextualized embeddings (ELMo, BERT).

📄 PDF Abstract BibTeX arXiv:1908.09369

Code (2)

sunipa/On-Measuring-and-Mitigating-Biased-Inferences-of-Word-Embeddings 공식 구현 pytorch
uclanlp/socialbias-dataset-construction-biases

Tasks

Natural Language InferenceWord Embeddings

Similar Papers 제목 키워드 기반

Detecting and Mitigating Indirect Stereotypes in Word Embeddings

2023-05-23 · Erin George, Joyce Chew, Deanna Needell

Societal biases in the usage of words, including harmful stereotypes, are frequently learned by common word embedding methods. These biases manifest not only between a word and an explicit marker of its stereotype, but a…

AttributeWord Embeddings

Mitigating Political Bias in Language Models Through Reinforced Calibration

2021-04-30 · Ruibo Liu, Chenyan Jia, Jason Wei, Guangxuan Xu 외

Current large-scale language models can be politically biased as a result of the data they are trained on, potentially causing serious problems when they are deployed in real-world settings. In this paper, we describe me…

reinforcement-learningReinforcement Learning (RL)Word Embeddings

Measuring Social Biases in Grounded Vision and Language Embeddings

2020-02-20 · NAACL 2021 4 · Candace Ross, Boris Katz, Andrei Barbu

We generalize the notion of social biases from language embeddings to grounded vision and language embeddings. Biases are present in grounded embeddings, and indeed seem to be equally or more significant than for ungroun…

Word Embeddings

A Causal Inference Method for Reducing Gender Bias in Word Embedding Relations

2019-11-25 · Zekun Yang, Juan Feng

Word embedding has become essential for natural language processing as it boosts empirical performances of various tasks. However, recent research discovers that gender bias is incorporated in neural word embeddings, and…

Causal Inferencecoreference-resolutionCoreference ResolutionSentence+1

OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings

2020-06-30 · EMNLP 2021 11 · Sunipa Dev, Tao Li, Jeff M. Phillips, Vivek Srikumar

Language representations are known to carry stereotypical biases and, as a result, lead to biased predictions in downstream tasks. While existing methods are effective at mitigating biases by linear projection, such meth…

Word Embeddings