no code implementations • BioNLP (ACL) 2022 • Usman Naseem, Ajay Bandi, Shaina Raza, Junaid Rashid, Bharathi Raja Chakravarthi
In this study, we propose a new method that addresses the challenges of medical dialogue generation by incorporating medical knowledge into transformer-based language models.
no code implementations • ACL (CASE) 2021 • Shaina Raza
Our proposed framework exploits the information from news articles and social contexts to detect fake news.
no code implementations • COLING 2022 • Shaina Raza, Syed Raza Bashir, Usman Naseem
We customize an augmented vector for each query and news item to introduce information interaction between the two towers.
1 code implementation • 1 Apr 2024 • Shaina Raza, Oluwanifemi Bamgbose, Shardul Ghuge, Fatemeh Tavakoli, Deepak John Reji
We introduce Safe and Responsible Large Language Model (SR$_{\text{LLM}}$) , a model designed to enhance the safety of language generation using LLMs.
no code implementations • 27 Mar 2024 • Zainab Al-Zanbouri, Gauri Sharma, Shaina Raza
These findings emphasize the importance of choosing ML models carefully to ensure both accuracy and fairness for all patients.
no code implementations • 14 Mar 2024 • Shaina Raza, Tahniat Khan, Drai Paulen-Patterson, Veronica Chatrath, Mizanur Rahman, Oluwanifemi Bamgbose
In today's technologically driven world, the rapid spread of fake news, particularly during critical events like elections, poses a growing threat to the integrity of information.
no code implementations • 20 Jan 2024 • Syed Raza Bashir, Shaina Raza, Vojislav Misic
As digital technology evolves, the increasing use of connected devices brings both challenges and opportunities in the areas of mobile crowdsourcing, edge computing, and recommender systems.
no code implementations • 19 Jan 2024 • Shaina Raza, Shardul Ghuge, Chen Ding, Elham Dolatabadi, Deval Pandya
The rapid evolution of Large Language Models (LLMs) highlights the necessity for ethical considerations and data integrity in AI development, particularly emphasizing the role of FAIR (Findable, Accessible, Interoperable, Reusable) data principles.
no code implementations • 12 Jan 2024 • Muskan Garg, MSVPJ Sathvik, Amrit Chadha, Shaina Raza, Sunghwan Sohn
The social NLP research community witness a recent surge in the computational advancements of mental health analysis to build responsible AI models for a complex interplay between language use and self-perception.
no code implementations • 1 Dec 2023 • Shaina Raza, Mizanur Rahman, Shardul Ghuge
Despite increasing awareness and research around fake news, there is still a significant need for datasets that specifically target racial slurs and biases within North American political speeches.
no code implementations • 30 Nov 2023 • Shaina Raza
The proliferation of biased news narratives across various media platforms has become a prominent challenge, influencing public opinion on critical topics like politics, health, and climate change.
no code implementations • 27 Nov 2023 • Tahniat Khan, Mizanur Rahman, Veronica Chatrath, Oluwanifemi Bamgbose, Shaina Raza
We have created a novel dataset of North American election-related news articles through a blend of advanced language models (LMs) and thorough human verification, for precision and relevance.
no code implementations • 20 Oct 2023 • Veronica Chatrath, Oluwanifemi Bamgbose, Shaina Raza
Additionally, implementing a test suite such as ours lowers the environmental overhead of making models safe and fair.
no code implementations • 30 Sep 2023 • Shaina Raza, Oluwanifemi Bamgbose, Veronica Chatrath, Shardul Ghuge, Yan Sidyakin, Abdullah Y Muaad
Bias detection in text is crucial for combating the spread of negative stereotypes, misinformation, and biased decision-making.
no code implementations • 3 Aug 2023 • Shaina Raza, Muskan Garg, Deepak John Reji, Syed Raza Bashir, Chen Ding
Therefore, it is crucial to detect and remove these biases to ensure the fair and ethical use of data.
no code implementations • 14 Jul 2023 • Shaina Raza, Chen Ding, Deval Pandya
Discriminatory language and biases are often present in hate speech during conversations, which usually lead to negative impacts on targeted groups such as those based on race, gender, and religion.
no code implementations • 11 May 2023 • Shaina Raza, Parisa Osivand Pour, Syed Raza Bashir
With the growing utilization of machine learning in healthcare, there is increasing potential to enhance healthcare outcomes.
no code implementations • 12 Apr 2023 • Shaina Raza
This study presents a machine learning (ML) pipeline for clinical data classification in the context of a 30-day readmission problem, along with a fairness audit on subgroups based on sensitive attributes.
no code implementations • 8 Apr 2023 • Shaina Raza
Machine learning (ML) has become a critical tool in public health, offering the potential to improve population health, diagnosis, treatment selection, and health system efficiency.
no code implementations • 20 Mar 2023 • Shaina Raza, Syed Raza Bashir
Infectious diseases are a significant public health concern globally, and extracting relevant information from scientific literature can facilitate the development of effective prevention and treatment strategies.
no code implementations • 13 Mar 2023 • Shaina Raza, Syed Raza Bashir, Sneha, Urooj Qamar
The concept of fairness is gaining popularity in academia and industry.
no code implementations • 11 Aug 2022 • Shaina Raza, Deepak John Reji, Chen Ding
Because of the increasing use of data-centric systems and algorithms in machine learning, the topic of fairness is receiving a lot of attention in the academic and broader literature.
no code implementations • 2 Aug 2022 • Syed Raza Bashir, Shaina Raza, Vojislav Misic
Our model combines location information and user preferences to provide more relevant recommendations compared to models that predict the next POI in a sequence.
1 code implementation • 8 Jul 2022 • Shaina Raza, Deepak John Reji, Dora D. Liu, Syed Raza Bashir, Usman Naseem
This paper introduces Dbias, which is a Python package to ensure fairness in news articles.
no code implementations • 2 Jul 2022 • Shaina Raza, Brian Schwartz
There are a few challenges related to the task of biomedical named entity recognition, which are: the existing methods consider a fewer number of biomedical entities (e. g., disease, symptom, proteins, genes); and these methods do not consider the social determinants of health (age, gender, employment, race), which are the non-medical factors related to patients' health.
no code implementations • 13 Jun 2022 • Shaina Raza
In this paper, we propose a machine learning pipeline capable of making predictions as well as detecting and mitigating biases in the data and model predictions.
no code implementations • 7 Jun 2022 • Shaina Raza
This problem motivates us to propose the design of the COVID-19 Search Engine (CO-SE), which is an algorithmic system that finds relevant documents for each query (asked by a user) and answers complex questions by searching a large corpus of publications.
no code implementations • 23 Mar 2021 • Shaina Raza
In a news recommender system, a reader's preferences change over time.
no code implementations • 15 Mar 2021 • Shaina Raza, Chen Ding
News reading is also driven by a blend of a reader's long-term and short-term interests.
no code implementations • 10 Sep 2020 • Shaina Raza, Chen Ding
Nowadays, more and more news readers tend to read news online where they have access to millions of news articles from multiple sources.