Viewing 1-10 of 10 papers
- Roy Schwartz, Jesse Dodge, Noah A. Smith, Oren EtzioniCACM • 2020 The computations required for deep learning research have been doubling every few months, resulting in an estimated 300,000x increase from 2012 to 2018 . These computations have a surprisingly large carbon footprint . Ironically, deep learning was inspired by the human brain, which is remarkably energy efficient. Moreover, the financial cost of the computations can make it difficult for academics, students, and researchers from emerging economies to engage in deep learning research. This position paper advocates a practical solution by making efficiency an evaluation criterion for research alongside accuracy and related measures. In addition, we propose reporting the financial cost or "price tag" of developing, training, and running models to provide baselines for the investigation of increasingly efficient methods. Our goal is to make AI both greener and more inclusive---enabling any inspired undergraduate with a laptop to write high-quality research papers. Green AI is an emerging focus at the Allen Institute for AI.
Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image RepresentationsTianlu Wang, Jieyu Zhao, Mark Yatskar, Kai-Wei Chang, Vicente OrdonezICCV • 2019In this work, we present a framework to measure and mitigate intrinsic biases with respect to protected variables --such as gender-- in visual recognition tasks. We show that trained models significantly amplify the association of target labels with gender beyond what one would expect from biased datasets. Surprisingly, we show that even when datasets are balanced such that each label co-occurs equally with each gender, learned models amplify the association between labels and gender, as much as if data had not been balanced! To mitigate this, we adopt an adversarial approach to remove unwanted features corresponding to protected variables from intermediate representations in a deep neural network -- and provide a detailed analysis of its effectiveness. Experiments on two datasets: the COCO dataset (objects), and the imSitu dataset (actions), show reductions in gender bias amplification while maintaining most of the accuracy of the original models.
- Maarten Sap, Dallas Card, Saadia Gabriel, Yejin Choi, Noah A. SmithACL • 2019 We investigate how annotators’ insensitivity to differences in dialect can lead to racial bias in automatic hate speech detection models, potentially amplifying harm against minority populations. We first uncover unexpected correlations between surface markers of African American English (AAE) and ratings of toxicity in several widely-used hate speech datasets. Then, we show that models trained on these corpora acquire and propagate these biases, such that AAE tweets and tweets by self-identified African Americans are up to two times more likely to be labelled as offensive compared to others. Finally, we propose dialect and race priming as ways to reduce the racial bias in annotation, showing that when annotators are made explicitly aware of an AAE tweet’s dialect they are significantly less likely to label the tweet as offensive.
Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding DatasetsMor Geva, Yoav Goldberg, Jonathan BerantarXiv • 2019Crowdsourcing has been the prevalent paradigm for creating natural language understanding datasets in recent years. A common crowdsourcing practice is to recruit a small number of high-quality workers, and have them massively generate examples. Having only a few workers generate the majority of examples raises concerns about data diversity, especially when workers freely generate sentences. In this paper, we perform a series of experiments showing these concerns are evident in three recent NLP datasets. We show that model performance improves when training with annotator identifiers as features, and that models are able to recognize the most productive annotators. Moreover, we show that often models do not generalize well to examples from annotators that did not contribute to the training set. Our findings suggest that annotator bias should be monitored during dataset creation, and that test set annotators should be disjoint from training set annotators.
- Gabriel Stanovsky, Noah A. Smith, Luke ZettlemoyerACL • 2019 We present the first challenge set and evaluation protocol for the analysis of gender bias in machine translation (MT). Our approach uses two recent coreference resolution datasets composed of English sentences which cast participants into non-stereotypical gender roles (e.g., "The doctor asked the nurse to help her in the operation"). We devise an automatic gender bias evaluation method for eight target languages with grammatical gender, based on morphological analysis (e.g., the use of female inflection for the word "doctor"). Our analyses show that four popular industrial MT systems and two recent state-of-the-art academic MT models are significantly prone to gender-biased translation errors for all tested target languages. Our data and code are made publicly available.
- Sergey Feldman, Waleed Ammar, Kyle Lo, Elly Trepman, Madeleine van Zuylen, Oren EtzioniJAMA • 2019 Importance: Analyses of female representation in clinical studies have been limited in scope and scale. Objective: To perform a large-scale analysis of global enrollment sex bias in clinical studies. Design, Setting, and Participants: In this cross-sectional study, clinical studies from published articles from PubMed from 1966 to 2018 and records from Aggregate Analysis of ClinicalTrials.gov from 1999 to 2018 were identified. Global disease prevalence was determined for male and female patients in 11 disease categories from the Global Burden of Disease database: cardiovascular, diabetes, digestive, hepatitis (types A, B, C, and E), HIV/AIDS, kidney (chronic), mental, musculoskeletal, neoplasms, neurological, and respiratory (chronic). Machine reading algorithms were developed that extracted sex data from tables in articles and records on December 31, 2018, at an artificial intelligence research institute. Male and female participants in 43 135 articles (792 004 915 participants) and 13 165 records (12 977 103 participants) were included. Main Outcomes and Measures: Sex bias was defined as the difference between the fraction of female participants in study participants minus prevalence fraction of female participants for each disease category. A total of 1000 bootstrap estimates of sex bias were computed by resampling individual studies with replacement. Sex bias was reported as mean and 95% bootstrap confidence intervals from articles and records in each disease category over time (before or during 1993 to 2018), with studies or participants as the measurement unit. Results: There were 792 004 915 participants, including 390 470 834 female participants (49%), in articles and 12 977 103 participants, including 6 351 619 female participants (49%), in records. With studies as measurement unit, substantial female underrepresentation (sex bias ≤ −0.05) was observed in 7 of 11 disease categories, especially HIV/AIDS (mean for articles, −0.17 [95% CI, −0.18 to −0.16]), chronic kidney diseases (mean, −0.17 [95% CI, −0.17 to −0.16]), and cardiovascular diseases (mean, −0.14 [95% CI, −0.14 to −0.13]). Sex bias in articles for all categories combined was unchanged over time with studies as measurement unit (range, −0.15 [95% CI, −0.16 to −0.13] to −0.10 [95% CI, −0.14 to −0.06]), but improved from before or during 1993 (mean, −0.11 [95% CI, −0.16 to −0.05]) to 2014 to 2018 (mean, −0.05 [95% CI, −0.09 to −0.02]) with participants as the measurement unit. Larger study size was associated with greater female representation. Conclusions and Relevance: Automated extraction of the number of participants in clinical reports provides an effective alternative to manual analysis of demographic bias. Despite legal and policy initiatives to increase female representation, sex bias against female participants in clinical studies persists. Studies with more participants have greater female representation. Differences between sex bias estimates with studies vs participants as measurement unit, and between articles vs records, suggest that sex bias with both measures and data sources should be reported.
- Lucy Lu Wang, Gabriel Stanovsky, Luca Weihs, Oren EtzioniarXiv • 2019 A comprehensive and up-to-date analysis of Computer Science literature (2.87 million papers through 2018) reveals that, if current trends continue, parity between the number of male and female authors will not be reached in this century. Under our most optimistic projection models, gender parity is forecast to be reached by 2100, and significantly later under more realistic assumptions. In contrast, parity is projected to be reached within two to three decades in the biomedical literature. Finally, our analysis of collaboration trends in Computer Science reveals decreasing rates of collaboration between authors of different genders.
Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove ThemHila Gonen, Yoav GoldbergNAACL • 2019Word embeddings are widely used in NLP for a vast range of tasks. It was shown that word embeddings derived from text corpora reflect gender biases in society. This phenomenon is pervasive and consistent across different word embedding models, causing serious concern. Several recent works tackle this problem, and propose methods for significantly reducing this gender bias in word embeddings, demonstrating convincing results. However, we argue that this removal is superficial. While the bias is indeed substantially reduced according to the provided bias definition, the actual effect is mostly hiding the bias, not removing it. The gender bias information is still reflected in the distances between “gender-neutralized” words in the debiased embeddings, and can be recovered from them. We present a series of experiments to support this claim, for two debiasing methods. We conclude that existing bias removal techniques are insufficient, and should not be trusted for providing gender-neutral modeling.
- Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordóñez, Kai-Wei ChangEMNLP • 2017 Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web. Structured prediction models are used in these tasks to take advantage of correlations between co-occurring labels and visual input but risk inadvertently encoding social biases found in web corpora. In this work, we study data and models associated with multilabel object classification and visual semantic role labeling. We find that (a) datasets for these tasks contain significant gender bias and (b) models trained on these datasets further amplify existing bias. For example, the activity cooking is over 33% more likely to involve females than males in a training set, and a trained model further amplifies the disparity to 68% at test time. We propose to inject corpus-level constraints for calibrating existing structured prediction models and design an algorithm based on Lagrangian relaxation for collective inference. Our method results in almost no performance loss for the underlying recognition task but decreases the magnitude of bias amplification by 47.5% and 40.5% for multilabel classification and visual semantic role labeling, respectively.
- Amitai Etzioni and Oren EtzioniCACM • 2016 Operational AI systems (for example, self-driving cars) need to obey both the law of the land and our values. We propose AI oversight systems ("AI Guardians") as an approach to addressing this challenge, and to respond to the potential risks associated with increasingly autonomous AI systems. These AI oversight systems serve to verify that operational systems did not stray unduly from the guidelines of their programmers and to bring them back in compliance if they do stray. The introduction of such second-order, oversight systems is not meant to suggest strict, powerful, or rigid (from here on 'strong') controls. Operations systems need a great degree of latitude in order to follow the lessons of their learning from additional data mining and experience and to be able to render at least semi-autonomous decisions (more about this later). However, all operational systems need some boundaries, both in order to not violate the law and to adhere to ethical norms. Developing such oversight systems, AI Guardians, is a major new mission for the AI community.