Human-centered Natural Language Processing

Par

Ines Arous

Université de Montréal

jeudi 7 mars 2024, 10:30-11:30 EST, Salle 6214

Pavillon André-Aisenstadt, Université de Montréal, 2920 Chemin de la Tour

Abstract: Natural Language Processing (NLP) has entered the public consciousness with widespread popularity, through platforms such as chatGPT. While responses from such a system are coherent, it may rely on inaccurate evidence, magnify ingrained biases, and lead to harmful outcomes. This alarming reality forces us to confront a fundamental research question: Can we rewire the very fabric of modern NLP models to align with human values? To tackle this question, my research focuses on a comprehensive reevaluation of the entire NLP pipeline. I posit that there is no one-size-fits-all solution to rectify the biases and ethical dilemmas plaguing NLP. Instead, I propose human-AI collaborative approaches where humans actively participate in all NLP pipeline stages from data annotation to model training and evaluation. In this talk, I will describe the steps to address this goal. First, I introduce a method integrating human annotation into the model's training process. Next, I explore enhancing models’ explainability by leveraging humans' rationale and evaluating them according to domain-specific requirements. Finally, I discuss the research opportunities for developing explainable and trustworthy NLP.

Bio: Ines is a Postdoctoral Researcher at Mila - Quebec AI Institute, affiliated with McGill University, where she works with Prof. Jackie C.K. Cheung at the intersection of human computation and natural language processing. She completed her Ph.D. at the University of Fribourg, Switzerland, under the supervision of Prof. Philippe Cudré-Mauroux, where she was awarded the best computer science thesis award in Switzerland. Her work has been centered on developing novel human-AI collaborative approaches for data curation. During her doctoral journey, she did an internship at Alexa Shopping, Amazon Research. She is passionate about leading the development of human-centered NLP models that are trustworthy, explainable, and effective.