Related papers: Interpretable bias mitigation for textual data: Re…
Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many important questions remain largely unanswered. In this work,…
Word vector representations are well developed tools for various NLP and Machine Learning tasks and are known to retain significant semantic and syntactic structure of languages. But they are prone to carrying and amplifying bias which can…
A common practice in the medical industry is the use of clinical notes, which consist of detailed patient observations. However, electronic health record systems frequently do not contain these observations in a structured format, rendering…
Texts like news, encyclopedias, and some social media strive for objectivity. Yet bias in the form of inappropriate subjectivity - introducing attitudes via framing, presupposing truth, and casting doubt - remains ubiquitous. This kind of…
Large language models like GPT-3.5-turbo and GPT-4 hold promise for healthcare professionals, but they may inadvertently inherit biases during their training, potentially affecting their utility in medical applications. Despite few attempts…
Language models (LMs) have become pivotal in the realm of technological advancements. While their capabilities are vast and transformative, they often include societal biases encoded in the human-produced datasets used for their training.…
Word embeddings derived from human-generated corpora inherit strong gender bias which can be further amplified by downstream models. Some commonly adopted debiasing approaches, including the seminal Hard Debias algorithm, apply…
Pre-trained language models encode undesirable social biases, which are further exacerbated in downstream use. To this end, we propose MABEL (a Method for Attenuating Gender Bias using Entailment Labels), an intermediate pre-training…
When translating "The secretary asked for details." to a language with grammatical gender, it might be necessary to determine the gender of the subject "secretary". If the sentence does not contain the necessary information, it is not…
An accurate and detailed account of patient medications, including medication changes within the patient timeline, is essential for healthcare providers to provide appropriate patient care. Healthcare providers or the patients themselves…
Data derived from the realm of the social sciences is often produced in digital text form, which motivates its use as a source for natural language processing methods. Researchers and practitioners have developed and relied on artificial…
Multimodal emotion recognition in conversations (mERC) is an active research topic in natural language processing (NLP), which aims to predict human's emotional states in communications of multiple modalities, e,g., natural language and…
Common methods for interpreting neural models in natural language processing typically examine either their structure or their behavior, but not both. We propose a methodology grounded in the theory of causal mediation analysis for…
Pre-trained language models (PLMs) have revolutionized both the natural language processing research and applications. However, stereotypical biases (e.g., gender and racial discrimination) encoded in PLMs have raised negative ethical…
Clinical notes in electronic health records contain highly heterogeneous writing styles, including non-standard terminology or abbreviations. Using these notes in predictive modeling has traditionally required preprocessing (e.g. taking…
As Machine Translation (MT) has become increasingly more powerful, accessible, and widespread, the potential for the perpetuation of bias has grown alongside its advances. While overt indicators of bias have been studied in machine…
In recent years, large Transformer-based Pre-trained Language Models (PLM) have changed the Natural Language Processing (NLP) landscape, by pushing the performance boundaries of the state-of-the-art on a wide variety of tasks. However, this…
Artificial intelligence (AI) systems, particularly those based on deep learning models, have increasingly achieved expert-level performance in medical applications. However, there is growing concern that such AI systems may reflect and…
Media bias detection requires comprehensive integration of information derived from multiple news sources. Sentence-level political bias detection in news is no exception, and has proven to be a challenging task that requires an…
Previous work has examined how debiasing language models affect downstream tasks, specifically, how debiasing techniques influence task performance and whether debiased models also make impartial predictions in downstream tasks or not.…