Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAn Overview of Fairness in Data -- Illuminating the Bias in Data Pipeline
نظرة عامة على الإنصاف في البيانات - إلقاء الضوء على التحيز في خط أنابيب البيانات
282
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
البيانات بشكل عام ترميز التحيزات البشرية بشكل افتراضي؛ إن إدراك هذه بداية جيدة، والبحث حول كيفية التعامل معها مستمر. يتم استخدام مصطلح التحيز على نطاق واسع في سياقات مختلفة في أنظمة NLP. في بحثنا، يكون التركيز محددا للتحيزات مثل النوع الاجتماعي والعنصرية والدين والوجهات الديمغرافية وغيرها من الآراء عند التحيزات التي تسود في أنظمة معالجة النصوص مسؤولة عن تمييز السكان المحددين بشكل منهجي، وهي ليست أخلاقية في NLP. تؤدي هذه التحيزات إلى تفاقم عدم المساواة والتنوع وإدراج السكان المحددين أثناء الاستفادة من تطبيقات NLP. تستخدم الأدوات والتكنولوجيا على المستوى المتوسط بيانات متحيزة، ونقل أو تضخيم هذا التحيز إلى تطبيقات المصب. ومع ذلك، لا يكفي أن تكون كافية، محايدة بين الجنسين وحدها عند تصميم تكنولوجيا غير متحيزة - بدلا من ذلك، يجب أن نأخذ جهدا واعيا من خلال تصميم إطار موحد لقياس وتحيز التحيز. في هذه الورقة، نوصي بستة تدابير وقياس زيادة واحدة بناء على ملاحظات التحيز في البيانات والشروح والتمثيلات النصية وتقنيات الدخل.
Data in general encodes human biases by default; being aware of this is a good start, and the research around how to handle it is ongoing. The term bias' is extensively used in various contexts in NLP systems. In our research the focus is specific to biases such as gender, racism, religion, demographic and other intersectional views on biases that prevail in text processing systems responsible for systematically discriminating specific population, which is not ethical in NLP. These biases exacerbate the lack of equality, diversity and inclusion of specific population while utilizing the NLP applications. The tools and technology at the intermediate level utilize biased data, and transfer or amplify this bias to the downstream applications. However, it is not enough to be colourblind, gender-neutral alone when designing a unbiased technology -- instead, we should take a conscious effort by designing a unified framework to measure and benchmark the bias. In this paper, we recommend six measures and one augment measure based on the observations of the bias in data, annotations, text representations and debiasing techniques.
References used
https://aclanthology.org/
rate research
Read More
Recent advances in NLP systems, notably the pretraining-and-finetuning paradigm, have achieved great success in predictive accuracy. However, these systems are usually not well calibrated for uncertainty out-of-the-box. Many recalibration methods hav
e been proposed in the literature for quantifying predictive uncertainty and calibrating model outputs, with varying degrees of complexity. In this work, we present a systematic study of a few of these methods. Focusing on the text classification task and finetuned large pretrained language models, we first show that many of the finetuned models are not well calibrated out-of-the-box, especially when the data come from out-of-domain settings. Next, we compare the effectiveness of a few widely-used recalibration methods (such as ensembles, temperature scaling). Then, we empirically illustrate a connection between distillation and calibration. We view distillation as a regularization term encouraging the student model to output uncertainties that match those of a teacher model. With this insight, we develop simple recalibration methods based on distillation with no additional inference-time cost. We show on the GLUE benchmark that our simple methods can achieve competitive out-of-domain (OOD) calibration performance w.r.t. more expensive approaches. Finally, we include ablations to understand the usefulness of components of our proposed method and examine the transferability of calibration via distillation.
Code-mixing is a phenomenon of mixing words and phrases from two or more languages in a single utterance of speech and text. Due to the high linguistic diversity, code-mixing presents several challenges in evaluating standard natural language generat
ion (NLG) tasks. Various widely popular metrics perform poorly with the code-mixed NLG tasks. To address this challenge, we present a metric in- dependent evaluation pipeline MIPE that significantly improves the correlation between evaluation metrics and human judgments on the generated code-mixed text. As a use case, we demonstrate the performance of MIPE on the machine-generated Hinglish (code-mixing of Hindi and English languages) sentences from the HinGE corpus. We can extend the proposed evaluation strategy to other code-mixed language pairs, NLG tasks, and evaluation metrics with minimal to no effort.
This paper presents the results of the shared tasks from the 8th workshop on Asian translation (WAT2021). For the WAT2021, 28 teams participated in the shared tasks and 24 teams submitted their translation results for the human evaluation. We also ac
cepted 5 research papers. About 2,100 translation results were submitted to the automatic evaluation server, and selected submissions were manually evaluated.
With the ever-increasing pace of research and high volume of scholarly communication, scholars face a daunting task. Not only must they keep up with the growing literature in their own and related fields, scholars increasingly also need to rebut pseu
do-science and disinformation. These needs have motivated an increasing focus on computational methods for enhancing search, summarization, and analysis of scholarly documents. However, the various strands of research on scholarly document processing remain fragmented. To reach out to the broader NLP and AI/ML community, pool distributed efforts in this area, and enable shared access to published research, we held the 2nd Workshop on Scholarly Document Processing (SDP) at NAACL 2021 as a virtual event (https://sdproc.org/2021/). The SDP workshop consisted of a research track, three invited talks, and three Shared Tasks (LongSumm 2021, SCIVER, and 3C). The program was geared towards the application of NLP, information retrieval, and data mining for scholarly documents, with an emphasis on identifying and providing solutions to open challenges.
Pre-trained neural language models give high performance on natural language inference (NLI) tasks. But whether they actually understand the meaning of the processed sequences is still unclear. We propose a new diagnostics test suite which allows to
assess whether a dataset constitutes a good testbed for evaluating the models' meaning understanding capabilities. We specifically apply controlled corruption transformations to widely used benchmarks (MNLI and ANLI), which involve removing entire word classes and often lead to non-sensical sentence pairs. If model accuracy on the corrupted data remains high, then the dataset is likely to contain statistical biases and artefacts that guide prediction. Inversely, a large decrease in model accuracy indicates that the original dataset provides a proper challenge to the models' reasoning capabilities. Hence, our proposed controls can serve as a crash test for developing high quality data for NLI tasks.
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
