Print Email Facebook Twitter Evaluating interpretability of state-of-the-art NLP models for predicting moral values Title Evaluating interpretability of state-of-the-art NLP models for predicting moral values Author Constantinescu, Ionut (TU Delft Electrical Engineering, Mathematics and Computer Science; TU Delft Intelligent Systems) Contributor Liscio, E. (mentor) Murukannaiah, P.K. (mentor) Marroquim, Ricardo (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2021-07-02 Abstract Understanding personal values is a crucial aspect that can facilitate the collaboration between AI and humans. Nonetheless, the implementation of collaborative agents in real life greatly depends on the amount of trust that is built in their relationship with people. In order to bridge this gap, more extensive analysis of the explainability of these systems needs to be conducted. We implement LSTM, BERT and FastText, three deep learning models for text classification and compare their interpretability on the task of predicting moral values from opinionated text. The results highlight the different degrees to which the behaviour of the three models can be explained in the context of moral value prediction. Our experiments showed that BERT, current state-of-the-art in natural language processing tasks, achieves the best performance while also providing more interpretable predictions than the other two models. Subject Moral foundationsMoral valuesNatural Language ProcessingExplainable AI To reference this document use: http://resolver.tudelft.nl/uuid:f8560b2b-8831-4c79-923a-9de785aa3c85 Embargo date 2022-12-31 Part of collection Student theses Document type bachelor thesis Rights © 2021 Ionut Constantinescu Files PDF Research_Paper_Ionut_Cons ... inescu.pdf 1.11 MB Close viewer /islandora/object/uuid%3Af8560b2b-8831-4c79-923a-9de785aa3c85/datastream/OBJ/view