Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology

Zmigrod, Ran; Mielke, Sebastian J.; Wallach, Hanna; Cotterell, Ryan

doi:10.48550/arxiv.1906.04571

Cited by 9 publications

(15 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been recently leveraged to alleviate the training data insufficiency problem in the machine learning community. In the past few years, this idea has achieved great successes in the fields of neural language processing (NLP) [41] and computer vision (CV) [2,6,12]. In this paper, we apply it to the top-N recommendation task, which, to the best of our knowledge, is the first time in this field.…”

Section: Related Workmentioning

confidence: 99%

“…At last, the new training samples are generated by actively changing the input variables (called intervention) and collecting the cared outputs. Such sample enrichment method has been successfully applied to the fields of neural language processing (NLP) [41] and computer vision (CV) [2,6,12]. In this paper, we adapt this method to the recommendation domain, which is expected to alleviate the contradiction between the more and more heavier neural recommender architectures and the sparse user behaviors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Top-N Recommendation with Counterfactual User Preference Simulation

Yang

Dai

Dong

et al. 2021

Proceedings of the 30th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Top-N recommendation, which aims to learn user ranking-based preference, has long been a fundamental problem in a wide range of applications. Traditional models usually motivate themselves by designing complex or tailored architectures based on different assumptions. However, the training data of recommender system can be extremely sparse and imbalanced, which poses great challenges for boosting the recommendation performance. To alleviate this problem, in this paper, we propose to reformulate the recommendation task within the causal inference framework, which enables us to counterfactually simulate user ranking-based preferences to handle the data scarce problem. The core of our model lies in the counterfactual question: "what would be the user's decision if the recommended items had been different?". To answer this question, we firstly formulate the recommendation process with a series of structural equation models (SEMs), whose parameters are optimized based on the observed data. Then, we actively indicate many recommendation lists (called intervention in the causal inference terminology) which are not recorded in the dataset, and simulate user feedback according to the learned SEMs for generating new training samples. Instead of randomly intervening on the recommendation list, we design a learning-based method to discover more informative training samples. Considering that the learned SEMs can be not perfect, we, at last, theoretically analyze the relation between the number of generated samples and the model prediction error, based on which a heuristic method is designed to control the negative effect brought by the prediction error. Extensive experiments are conducted based on both synthetic and real-world datasets to demonstrate the effectiveness of our framework. CCS CONCEPTS• Information systems → Recommender systems.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Top-N Recommendation with Counterfactual User Preference Simulation

Yang

Dai

Dong

et al. 2021

Proceedings of the 30th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

show abstract

“…assumption. This is the standard approach to using this kind of data, and it has been done numerous times previously (Andreas, 2019;Zmigrod et al, 2019). This is not applicable if the bundle was obtained by mining the existing training instances, however.…”

Section: Alternative Uses Of Bundlesmentioning

confidence: 99%

Learning with Instance Bundles for Reading Comprehension

Dua¹,

Dasigi²,

Singh³

et al. 2021

Preprint

View full text Add to dashboard Cite

When training most modern reading comprehension models, all the questions associated with a context are treated as being independent from each other. However, closely related questions and their corresponding answers are not independent, and leveraging these relationships could provide a strong supervision signal to a model. Drawing on ideas from contrastive estimation, we introduce several new supervision techniques that compare question-answer scores across multiple related instances. Specifically, we normalize these scores across various neighborhoods of closely contrasting questions and/or answers, adding another cross entropy loss term that is used in addition to traditional maximum likelihood estimation. Our techniques require bundles of related question-answer pairs, which we can either mine from within existing data or create using various automated heuristics. We empirically demonstrate the effectiveness of training with instance bundles on two datasets-HotpotQA and ROPES-showing up to 11% absolute gains in accuracy.

show abstract

“…Consequently, recent works in bias measurement or mitigation have adopted generative models which can synthesize or manipulate text or image data (Denton et al, 2019;Zmigrod et al, 2019). These methods generate hypothetical data in which only sensitive attributes are switched.…”

Section: Counterfactual Data Synthesismentioning

confidence: 99%

Gender Slopes: Counterfactual Fairness for Computer Vision Models by Attribute Manipulation

Joo,

Kärkkäinen

2020

Preprint

View full text Add to dashboard Cite

Automated computer vision systems have been applied in many domains including security, law enforcement, and personal devices, but recent reports suggest that these systems may produce biased results, discriminating against people in certain demographic groups. Diagnosing and understanding the underlying true causes of model biases, however, are challenging tasks because modern computer vision systems rely on complex black-box models whose behaviors are hard to decode. We propose to use an encoder-decoder network developed for image attribute manipulation to synthesize facial images varying in the dimensions of gender and race while keeping other signals intact. We use these synthesized images to measure counterfactual fairness of commercial computer vision classifiers by examining the degree to which these classifiers are affected by gender and racial cues controlled in the images, e.g., feminine faces may elicit higher scores for the concept of nurse and lower scores for STEM-related concepts. We also report the skewed gender representations in an online search service on profession-related keywords, which may explain the origin of the biases encoded in the models.

show abstract

Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology

Cited by 9 publications

References 16 publications

Top-N Recommendation with Counterfactual User Preference Simulation

Top-N Recommendation with Counterfactual User Preference Simulation

Learning with Instance Bundles for Reading Comprehension

Gender Slopes: Counterfactual Fairness for Computer Vision Models by Attribute Manipulation

Contact Info

Product

Resources

About