Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userUnpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens
تفريغ النظم المترابطة للتمييز: التحيز القلوع في أنظمة NLP من خلال عدسة تقاطع
695
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تجرب الكثير من سكان العالم بعض أشكال الإعاقة خلال حياتهم.يجب ممارسة الحذر أثناء تصميم أنظمة معالجة اللغة الطبيعية (NLP) لمنع الأنظمة من إدامة التحيز القوي عن غير قصد ضد الأشخاص ذوي الإعاقة، أي الإخلال بفضل القدرات النموذجية.نبلغ عن التحليلات المختلفة بناء على تنبؤات كلمة لنموذج لغة بيرت واسعة النطاق.تظهر النتائج ذات دلالة إحصائية أن الأشخاص ذوي الإعاقة يمكنين محرومين.استكشاف النتائج أيضا أشكال التمييز المتداخلة المتعلقة بالجنس المترابط والهويات العرقية.
Much of the world's population experiences some form of disability during their lifetime. Caution must be exercised while designing natural language processing (NLP) systems to prevent systems from inadvertently perpetuating ableist bias against people with disabilities, i.e., prejudice that favors those with typical abilities. We report on various analyses based on word predictions of a large-scale BERT language model. Statistically significant results demonstrate that people with disabilities can be disadvantaged. Findings also explore overlapping forms of discrimination related to interconnected gender and race identities.
References used
https://aclanthology.org/
rate research
Read More
HCI and NLP traditionally focus on different evaluation methods. While HCI involves a small number of people directly and deeply, NLP traditionally relies on standardized benchmark evaluations that involve a larger number of people indirectly. We pre
sent five methodological proposals at the intersection of HCI and NLP and situate them in the context of ML-based NLP models. Our goal is to foster interdisciplinary collaboration and progress in both fields by emphasizing what the fields can learn from each other.
Question answering (QA) models use retriever and reader systems to answer questions. Reliance on training data by QA systems can amplify or reflect inequity through their responses. Many QA models, such as those for the SQuAD dataset, are trained and
tested on a subset of Wikipedia articles which encode their own biases and also reproduce real-world inequality. Understanding how training data affects bias in QA systems can inform methods to mitigate inequity. We develop two sets of questions for closed and open domain questions respectively, which use ambiguous questions to probe QA models for bias. We feed three deep-learning-based QA systems with our question sets and evaluate responses for bias via the metrics. Using our metrics, we find that open-domain QA models amplify biases more than their closed-domain counterparts and propose that biases in the retriever surface more readily due to greater freedom of choice.
Natural Language Processing (NLP) is defined by specific, separate tasks, with each their own literature, benchmark datasets, and definitions. In this position paper, we argue that for a complex problem such as the threat to democracy by non-diverse
news recommender systems, it is important to take into account a higher-order, normative goal and its implications. Experts in ethics, political science and media studies have suggested that news recommendation systems could be used to support a deliberative democracy. We reflect on the role of NLP in recommendation systems with this specific goal in mind and show that this theory of democracy helps to identify which NLP tasks and techniques can support this goal, and what work still needs to be done. This leads to recommendations for NLP researchers working on this specific problem as well as researchers working on other complex multidisciplinary problems.
Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model that leverages the document structure to provide dialo
gue-contextualized passage encodings and better locate knowledge relevant to the conversation. An auxiliary loss captures the history of dialogue-document connections. We demonstrate the effectiveness of our model on two document-grounded conversational datasets and provide analyses showing generalization to unseen documents and long dialogue contexts.
We analyze 6.7 million case law documents to determine the presence of gender bias within our judicial system. We find that current bias detection methods in NLP are insufficient to determine gender bias in our case law database and propose an altern
ative approach. We show that existing algorithms' inconsistent results are consequences of prior research's inconsistent definitions of biases themselves. Bias detection algorithms rely on groups of words to represent bias (e.g., salary,' job,' and boss' to represent employment as a potentially biased theme against women in text). However, the methods to build these groups of words have several weaknesses, primarily that the word lists are based on the researchers' own intuitions. We suggest two new methods of automating the creation of word lists to represent biases. We find that our methods outperform current NLP bias detection methods. Our research improves the capabilities of NLP technology to detect bias and highlights gender biases present in influential case law. In order to test our NLP bias detection method's performance, we regress our results of bias in case law against U.S census data of women's participation in the workforce in the last 100 years.
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
