Data Science Seminars - Rationale Trees: Towards a Formalization of Human Knowledge for Explainable Natural Language Processing
Presenter: Andrea Tocchetti
PHD Student in Information Technology
DEIB - Data Science and Bioinformatics Lab (Bld.21)
April 16th, 2025 - 5.00 pm
Contact: Silvia Cascianelli
PHD Student in Information Technology
DEIB - Data Science and Bioinformatics Lab (Bld.21)
April 16th, 2025 - 5.00 pm
Contact: Silvia Cascianelli
Sommario
On April 16th, 2025 at 5.00 pm a new appointment of Data Science Seminars series titled "Rationale Trees: Towards a Formalization of Human Knowledge for Explainable Natural Language Processing" will take place at DEIB Data Science and Bioinformatics Lab (Building 21).
During this talk, we will have, as speaker, Andrea Tocchetti, PHD Student at Dipartimento di Elettronica, Informazione e Bioingegneria.
Explainable Artificial Intelligence (XAI) approaches have been widely applied to NLP models, although the explanations they provide may still be complex to understand for human interpreters as these may not be aligned with the reasoning process they apply in language-based tasks. We propose ad hoc formalizations to bridge the gap between model and human reasoning that structure and detail the thought process applied by human interpreters when performing an NLP task.
The Data Science Seminars meetings are primarily meant for all the 'Data Science and Bioinformatics lab' members, but anyone potentially interested in the topics is more than welcome to attend.
During this talk, we will have, as speaker, Andrea Tocchetti, PHD Student at Dipartimento di Elettronica, Informazione e Bioingegneria.
Explainable Artificial Intelligence (XAI) approaches have been widely applied to NLP models, although the explanations they provide may still be complex to understand for human interpreters as these may not be aligned with the reasoning process they apply in language-based tasks. We propose ad hoc formalizations to bridge the gap between model and human reasoning that structure and detail the thought process applied by human interpreters when performing an NLP task.
The Data Science Seminars meetings are primarily meant for all the 'Data Science and Bioinformatics lab' members, but anyone potentially interested in the topics is more than welcome to attend.
