Model compression techniques are receiving increasing attention; however, the effect of compression on model fairness is still under explored. This is the first paper to examine the effect of distillation and pruning on the toxicity and bias of generative language models. We test Knowledge Distillation and Pruning methods on the GPT2 model and found a consistent pattern of toxicity and bias reduction after model distillation; this result can be potentially interpreted by existing line of research which describes model compression as a regularization technique; our work not only serves as a reference for safe deployment of compressed models, but also extends the discussion of "compression as regularization" into the setting of neural LMs, and hints at the possibility of using compression to develop fairer models.
Recent research has revealed undesirable biases in NLP data and models. However, these efforts focus on social disparities in West, and are not directly portable to other geo-cultural contexts. In this paper, we focus on NLP fair-ness in the context of India. We start with a brief account of the prominent axes of social disparities in India. We build resources for fairness evaluation in the Indian context and use them to demonstrate prediction biases along some of the axes. We then delve deeper into social stereotypes for Region andReligion, demonstrating its prevalence in corpora and models. …
Recent research has revealed undesirable biases in NLP data and models. However, these efforts largely focus on social disparities in the West, and are not directly portable to other geo-cultural contexts. In this position paper, we outline a holistic research agenda to re-contextualize NLP fairness research for the Indian context, accounting for Indian societal context, bridging technological gaps in capability and resources, and adapting to Indian cultural values. We also summarize findings from an empirical study on various social biases along different axes of disparities relevant to India…
Motivations for methods in explainable artificial intelligence (XAI) often include detecting, quantifying and mitigating bias, and contributing to making machine learning models fairer. However, exactly how an XAI method can help in combating biases is often left unspecified. In this paper, we briefly review trends in explainability and fairness in NLP research, identify the current practices in which explainability methods are applied to detect and mitigate bias, and investigate the barriers preventing XAI methods from being used more widely in tackling fairness issues.
Measuring bias is key for better understanding and addressing unfairness in NLP/ML models. This is often done via fairness metrics which quantify the differences in a model's behaviour across a range of demographic groups. In this work, we shed more light on the differences and similarities between the fairness metrics used in NLP. First, we unify a broad range of existing metrics under three generalized fairness metrics, revealing the connections between them. Next, we carry out an extensive empirical comparison of existing metrics and demonstrate that the observed differences in bias measure…
University of Illinois Chicago（伊利诺伊大学芝加哥分校）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Arizona State University（亚利桑那州立大学）
Natural Language Processing (NLP) models have been found discriminative against groups of different social identities such as gender and race. With the negative consequences of these undesired biases, researchers have responded with unprecedented effort and proposed promising approaches for bias mitigation. In spite of considerable practical importance, current algorithmic fairness literature lacks an in-depth understanding of the relations between different forms of biases. Social bias is complex by nature. Numerous studies in social psychology identify the "generalized prejudice", i.e., gene…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；University of Western Ontario（西安大略大学）；St. Michael’s Hospital（圣迈克尔医院）
Clinical machine learning is increasingly multimodal, collected in both structured tabular formats and unstructured forms such as freetext. We propose a novel task of exploring fairness on a multimodal clinical dataset, adopting equalized odds for the downstream medical prediction tasks. To this end, we investigate a modality-agnostic fairness algorithm - equalized odds post processing - and compare it to a text-specific fairness algorithm: debiased clinical word embeddings. Despite the fact that debiased word embeddings do not explicitly address equalized odds of protected groups, we show tha…
University of Mannheim（曼海姆大学）；Carnegie Mellon University（卡内基梅隆大学）；Bocconi University（博科尼大学）；University of Hamburg（汉堡大学）
Fairness and environmental impact are important research directions for the sustainable development of artificial intelligence. However, while each topic is an active research area in natural language processing (NLP), there is a surprising lack of research on the interplay between the two fields. This lacuna is highly problematic, since there is increasing evidence that an exclusive focus on fairness can actually hinder environmental sustainability, and vice versa. In this work, we shed light on this crucial intersection in NLP by (1) investigating the efficiency of current fairness approache…
The University of Melbourne（墨尔本大学）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）
Modern NLP systems exhibit a range of biases, which a growing literature on model debiasing attempts to correct. However current progress is hampered by a plurality of definitions of bias, means of quantification, and oftentimes vague relation between debiasing algorithms and theoretical measures of bias. This paper seeks to clarify the current situation and plot a course for meaningful progress in fair learning, with two key contributions: (1) making clear inter-relations among the current gamut of methods, and their relation to fairness theory; and (2) addressing the practical problem of mod…
As NLP models become more integrated with the everyday lives of people, it becomes important to examine the social effect that the usage of these systems has. While these models understand language and have increased accuracy on difficult downstream tasks, there is evidence that these models amplify gender, racial and cultural stereotypes and lead to a vicious cycle in many settings. In this survey, we analyze the origins of biases, the definitions of fairness, and how different subfields of NLP mitigate bias. We finally discuss how future studies can work towards eradicating pernicious biases…
Center for Artificial Intelligence Research (CAiRE)（人工智能研究中心（CAiRE））；The Hong Kong University of Science and Technology（香港科技大学）
Despite their ubiquity in NLP tasks, Long Short-Term Memory (LSTM) networks suffer from computational inefficiencies caused by inherent unparallelizable recurrences, which further aggravates as LSTMs require more parameters for larger memory capacity. In this paper, we propose to apply low-rank matrix factorization (MF) algorithms to different recurrences in LSTMs, and explore the effectiveness on different NLP tasks and model components. We discover that additive recurrence is more important than multiplicative recurrence, and explain this by identifying meaningful correlations between matrix…
Google Research（谷歌研究院）；University of Cambridge（剑桥大学）；University of Copenhagen（哥本哈根大学）
The prototypical NLP experiment trains a standard architecture on labeled English data and optimizes for accuracy, without accounting for other dimensions such as fairness, interpretability, or computational efficiency. We show through a manual classification of recent NLP research papers that this is indeed the case and refer to it as the square one experimental setup. We observe that NLP research often goes beyond the square one setup, e.g, focusing not only on accuracy, but also on fairness or interpretability, but typically only along a single dimension. Most work targeting multilinguality…
SambaNova Systems（桑巴诺瓦系统公司）；AMD Research（AMD研究院）；Arm ML Research（Arm机器学习研究院）
Sequence model based NLP applications can be large. Yet, many applications that benefit from them run on small devices with very limited compute and storage capabilities, while still having run-time constraints. As a result, there is a need for a compression technique that can achieve significant compression without negatively impacting inference run-time and task accuracy. This paper proposes a new compression technique called Hybrid Matrix Factorization that achieves this dual objective. HMF improves low-rank matrix factorization (LMF) techniques by doubling the rank of the matrix using an i…
Encoded text representations often capture sensitive attributes about individuals (e.g., race or gender), which raise privacy concerns and can make downstream models unfair to certain groups. In this work, we propose FEDERATE, an approach that combines ideas from differential privacy and adversarial training to learn private text representations which also induces fairer models. We empirically evaluate the trade-off between the privacy of the representations and the fairness and accuracy of the downstream model on four NLP datasets. Our results show that FEDERATE consistently improves upon pre…
Recent transformer language models achieve outstanding results in many natural language processing (NLP) tasks. However, their enormous size often makes them impractical on memory-constrained devices, requiring practitioners to compress them to smaller networks. In this paper, we explore offline compression methods, meaning computationally-cheap approaches that do not require further fine-tuning of the compressed model. We challenge the classical matrix factorization methods by proposing a novel, better-performing autoencoder-based framework. We perform a comprehensive ablation study of our ap…
Finding Pareto Trade-offs in Fair and Accurate Detection of Toxic Speech
Dept. of Computer Science, The University of Texas at Austin（德克萨斯大学奥斯汀分校计算机科学系）；School of Computer Science, The University of Birmingham（伯明翰大学计算机科学学院）；School of Information, The University of Texas at Austin（德克萨斯大学奥斯汀分校信息学院）；McCombs School of Business, The University of Texas at Austin（德克萨斯大学奥斯汀分校麦科姆商学院）
Examining risks of racial biases in NLP tools for child protective services
Johns Hopkins University（约翰斯·霍普金斯大学）；Carnegie Mellon University（卡内基梅隆大学）；Microsoft Research NYC（微软纽约研究院）；The University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；University of Washington（华盛顿大学）
University of Copenhagen（哥本哈根大学）；National University of Defense Technology（国防科技大学）
We present a benchmark suite of four datasets for evaluating the fairness of pre-trained language models and the techniques used to fine-tune them for downstream tasks. Our benchmarks cover four jurisdictions (European Council, USA, Switzerland, and China), five languages (English, German, French, Italian and Chinese) and fairness across five attributes (gender, age, region, language, and legal area). In our experiments, we evaluate pre-trained language models using several group-robust fine-tuning techniques and show that performance group disparities are vibrant in many cases, while none of …
School of Computing and Information Systems, University of Melbourne（墨尔本大学计算与信息系统学院）；School of Information Technology and Electrical Engineering, University of Queensland（昆士兰大学信息技术与电气工程学院）
Class imbalance is a common challenge in many NLP tasks, and has clear connections to bias, in that bias in training data often leads to higher accuracy for majority groups at the expense of minority groups. However there has traditionally been a disconnect between research on class-imbalanced learning and mitigating bias, and only recently have the two been looked at through a common lens. In this work we evaluate long-tail learning methods for tweet sentiment and occupation classification, and extend a margin-loss based approach with methods to enforce fairness. We empirically show through c…
Despite achieving state-of-the-art performance on many NLP tasks, the high energy cost and long inference delay prevent Transformer-based pretrained language models (PLMs) from seeing broader adoption including for edge and mobile computing. Efficient NLP research aims to comprehensively consider computation, time and carbon emission for the entire life-cycle of NLP, including data preparation, model training and inference. In this survey, we focus on the inference stage and review the current state of model compression and acceleration for pretrained language models, including benchmarks, met…
Neural models often exploit superficial features to achieve good performance, rather than deriving more general features. Overcoming this tendency is a central challenge in areas such as representation learning and ML fairness. Recent work has proposed using data augmentation, i.e., generating training examples where the superficial features fail, as a means of encouraging models to prefer the stronger features. We design a series of toy learning problems to test the hypothesis that data augmentation leads models to unlearn weaker heuristics, but not to learn stronger features in their place. …
Technische Universität Darmstadt（达姆施塔特工业大学）；Nanyang Technological University（南洋理工大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
Obstacles hindering the development of capsule networks for challenging NLP applications include poor scalability to large output spaces and less reliable routing processes. In this paper, we introduce: 1) an agreement score to evaluate the performance of routing processes at instance level; 2) an adaptive optimizer to enhance the reliability of routing; 3) capsule compression and partial routing to improve the scalability of capsule networks. We validate our approach on two NLP tasks, namely: multi-label text classification and question answering. Experimental results show that our approach c…
Pre-trained language models have been applied to various NLP tasks with considerable performance gains. However, the large model sizes, together with the long inference time, limit the deployment of such models in real-time applications. One line of model compression approaches considers knowledge distillation to distill large teacher models into small student models. Most of these studies focus on single-domain only, which ignores the transferable knowledge from other domains. We notice that training a teacher with transferable knowledge digested across domains can achieve better generalizati…
Natural language processing (NLP) models often require a massive number of parameters for word embeddings, resulting in a large storage or memory footprint. Deploying neural NLP models to mobile devices requires compressing the word embeddings without any significant sacrifices in performance. For this purpose, we propose to construct the embeddings with few basis vectors. For each word, the composition of basis vectors is determined by a hash code. To maximize the compression rate, we adopt the multi-codebook quantization approach instead of binary coding scheme. Each code is composed of mult…
Apple（苹果公司）；Cornell Tech（康奈尔大学科技校区）；Massachusetts Institute of Technology（麻省理工学院）
Quantization, knowledge distillation, and magnitude pruning are among the most popular methods for neural network compression in NLP. Independently, these methods reduce model size and can accelerate inference, but their relative benefit and combinatorial interactions have not been rigorously studied. For each of the eight possible subsets of these techniques, we compare accuracy vs. model size tradeoffs across six BERT architecture sizes and eight GLUE tasks. We find that quantization and distillation consistently provide greater benefit than pruning. Surprisingly, except for the pair of prun…
In recent years, the fields of natural language processing (NLP) and information retrieval (IR) have made tremendous progress thanksto deep learning models like Recurrent Neural Networks (RNNs), Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTMs)networks, and Transformer [120] based models like Bidirectional Encoder Representations from Transformers (BERT) [24], GenerativePre-training Transformer (GPT-2) [94], Multi-task Deep Neural Network (MT-DNN) [73], Extra-Long Network (XLNet) [134], Text-to-text transfer transformer (T5) [95], T-NLG [98] and GShard [63]. But these models are …
Pre-trained language models of the BERT family have defined the state-of-the-arts in a wide range of NLP tasks. However, the performance of BERT-based models is mainly driven by the enormous amount of parameters, which hinders their application to resource-limited scenarios. Faced with this problem, recent studies have been attempting to compress BERT into a small-scale model. However, most previous work primarily focuses on a single kind of compression technique, and few attention has been paid to the combination of different methods. When BERT is compressed with integrated techniques, a crit…
Pre-trained Language Models (PLMs) have been successful for a wide range of natural language processing (NLP) tasks. The state-of-the-art of PLMs, however, are extremely large to be used on edge devices. As a result, the topic of model compression has attracted increasing attention in the NLP community. Most of the existing works focus on compressing encoder-based models (tiny-BERT, distilBERT, distilRoBERTa, etc), however, to the best of our knowledge, the compression of decoder-based models (such as GPT-2) has not been investigated much. Our paper aims to fill this gap. Specifically, we expl…
Microsoft Dynamics 365 AI Research（微软Dynamics 365人工智能研究院）
Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application in practice. In order to alleviate this resource hunger in large-scale model training, we propose a Patient Knowledge Distillation approach to compress an original large model (teacher) into an equally-effective lightweight shallow network (student). Different from previous knowledge distillation methods, which only use the output from the last layer of the teacher network for …
Colombian Waitresses y Jueces canadienses: Gender and Country Biases in Occupation Recommendations from LLMs
Erasmus Mundus Master in Language and Communication Technologies（埃拉斯谟 Mundus 语言与沟通技术硕士项目）；HiTZ Center - Ixa, University of the Basque Country (UPV/EHU)（巴斯克国家大学（UPV/EHU）HiTZ中心 - Ixa）；Cohere（Cohere公司）；Saarland University（萨尔兰州大学）
Data-driven predictive solutions predominant in commercial applications tend to suffer from biases and stereotypes, which raises equity concerns. Prediction models may discover, use, or amplify spurious correlations based on gender or other protected personal characteristics, thus discriminating against marginalized groups. Mitigating gender bias has become an important research focus in natural language processing (NLP) and is an area where annotated corpora are available. Data augmentation reduces gender bias by adding counterfactual examples to the training dataset. In this work, we show th…
