Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userQuantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics
تحديد التحيزات الاجتماعية في NLP: تعميم ومقارنة تجريبية لمقاييس الإنصاف الخارجي
205
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تحيز قياس التجريدي هو المفتاح لفهم أفضل ومعالجة الظلم في نماذج NLP / ML.غالبا ما يتم ذلك عبر مقاييس الإنصاف، مما يحدد الاختلافات في سلوك النموذج عبر مجموعة من المجموعات الديموغرافية.في هذا العمل، ألقينا المزيد من الضوء على الاختلافات وتشابه التشابه بين مقاييس الإنصاف المستخدمة في NLP.أولا، نقوم بتوحيد مجموعة واسعة من المقاييس الموجودة بموجب ثلاثة مقاييس المعرفة المعممة، وكشف عن الاتصالات بينهما.بعد ذلك، نقوم بإجراء مقارنة تجريبية واسعة النطاق للمقاييس الموجودة وإظهار أن الاختلافات المرصودة في قياس التحيز يمكن تفسيرها بشكل منهجي عبر الاختلافات في خيارات المعلمات لمقاييسنا المعمم.
Abstract 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 measurement can be systematically explained via differences in parameter choices for our generalized metrics.
References used
https://aclanthology.org/
rate research
Read More
We generalize the notion of measuring social biases in word embeddings to visually grounded word embeddings. Biases are present in grounded embeddings, and indeed seem to be equally or more significant than for ungrounded embeddings. This is despite
the fact that vision and language can suffer from different biases, which one might hope could attenuate the biases in both. Multiple ways exist to generalize metrics measuring bias in word embeddings to this new setting. We introduce the space of generalizations (Grounded-WEAT and Grounded-SEAT) and demonstrate that three generalizations answer different yet important questions about how biases, language, and vision interact. These metrics are used on a new dataset, the first for grounded bias, created by augmenting standard linguistic bias benchmarks with 10,228 images from COCO, Conceptual Captions, and Google Images. Dataset construction is challenging because vision datasets are themselves very biased. The presence of these biases in systems will begin to have real-world consequences as they are deployed, making carefully measuring bias and then mitigating it critical to building a fair society.
Humans can learn a new language task efficiently with only few examples, by leveraging their knowledge obtained when learning prior tasks. In this paper, we explore whether and how such cross-task generalization ability can be acquired, and further a
pplied to build better few-shot learners across diverse NLP tasks. We introduce CrossFit, a problem setup for studying cross-task generalization ability, which standardizes seen/unseen task partitions, data access during different learning stages, and the evaluation protocols. To instantiate different seen/unseen task partitions in CrossFit and facilitate in-depth analysis, we present the NLP Few-shot Gym, a repository of 160 diverse few-shot NLP tasks created from open-access NLP datasets and converted to a unified text-to-text format. Our analysis reveals that the few-shot learning ability on unseen tasks can be improved via an upstream learning stage using a set of seen tasks. We also observe that the selection of upstream learning tasks can significantly influence few-shot performance on unseen tasks, asking further analysis on task similarity and transferability.
Online social media platforms increasingly rely on Natural Language Processing (NLP) techniques to detect abusive content at scale in order to mitigate the harms it causes to their users. However, these techniques suffer from various sampling and ass
ociation biases present in training data, often resulting in sub-par performance on content relevant to marginalized groups, potentially furthering disproportionate harms towards them. Studies on such biases so far have focused on only a handful of axes of disparities and subgroups that have annotations/lexicons available. Consequently, biases concerning non-Western contexts are largely ignored in the literature. In this paper, we introduce a weakly supervised method to robustly detect lexical biases in broader geo-cultural contexts. Through a case study on a publicly available toxicity detection model, we demonstrate that our method identifies salient groups of cross-geographic errors, and, in a follow up, demonstrate that these groupings reflect human judgments of offensive and inoffensive language in those geographic contexts. We also conduct analysis of a model trained on a dataset with ground truth labels to better understand these biases, and present preliminary mitigation experiments.
The field of NLP has made substantial progress in building meaning representations. However, an important aspect of linguistic meaning, social meaning, has been largely overlooked. We introduce the concept of social meaning to NLP and discuss how insights from sociolinguistics can inform work on representation learning in NLP. We also identify key challenges for this new line of research.
NLP systems rarely give special consideration to numbers found in text. This starkly contrasts with the consensus in neuroscience that, in the brain, numbers are represented differently from words. We arrange recent NLP work on numeracy into a compre
hensive taxonomy of tasks and methods. We break down the subjective notion of numeracy into 7 subtasks, arranged along two dimensions: granularity (exact vs approximate) and units (abstract vs grounded). We analyze the myriad representational choices made by over a dozen previously published number encoders and decoders. We synthesize best practices for representing numbers in text and articulate a vision for holistic numeracy in NLP, comprised of design trade-offs and a unified evaluation.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
