Meta Lifelong-Learning With Selective and Task-Aware Adaptation

Autor: Thanapapas Horsuwan, Piyawat Lertvittayakumjorn, Kasidis Kanwatchara, Boonserm Kijsirikul, Peerapon Vateekul

Publikováno v: IEEE Access, Vol 12, Pp 34099-34115 (2024)

Meta-learning has been applied to lifelong language learning due to its ability to find an optimal model for efficient adaptation to any learned tasks. Generally, meta lifelong-learning partially stores samples from seen tasks in a memory and selects

Externí odkaz: https://doaj.org/article/289dbfd7474049c3983689a1b92778fa

Argumentative explanations for pattern-based text classifiers

Autor: Piyawat Lertvittayakumjorn, Francesca Toni

Publikováno v: Argument & Computation, Pp 1-72 (2023)

Recent works in Explainable AI mostly address the transparency issue of black-box models or create explanations for any kind of models (i.e., they are model-agnostic), while leaving explanations of interpretable models largely underexplored. In this

Externí odkaz: https://doaj.org/article/1221f831233c49d28451adb064d5533b

Enhancing Lifelong Language Learning by Improving Pseudo-Sample Generation

Autor: Kasidis Kanwatchara, Thanapapas Horsuwan, Piyawat Lertvittayakumjorn, Boonserm Kijsirikul, Peerapon Vateekul

Publikováno v: Computational Linguistics, Vol 48, Iss 4 (2022)

To achieve lifelong language learning, pseudo-rehearsal methods leverage samples generated from a language model to refresh the knowledge of previously learned tasks. Without proper controls, however, these methods could fail to retain the knowledge

Externí odkaz: https://doaj.org/article/144d323fe8a146849b81ca4f653a6e7a

Exploratory Analysis for Big Social Data Using Deep Network

Autor: Chao Wu, Guolong Wang, Jiangcheng Zhu, Piyawat Lertvittayakumjorn, Simon Hu, Chilie Tan, Hong Mi, Yadan Xu, Jun Xiao

Publikováno v: IEEE Access, Vol 7, Pp 21446-21453 (2019)

Exploratory analysis is an important way to gain understanding and find unknown relationships from various data sources, especially in the era of big data. Traditional paradigms of social science data analysis follow the steps of feature selection, m

Externí odkaz: https://doaj.org/article/27b879b996c04d138f301945d6c38d6d

Neural QBAFs: explaining neural networks under LRP-based argumentation frameworks

Autor: Purin Sukpanichnant, Antonio Rago, Piyawat Lertvittayakumjorn, Francesca Toni

Publikováno v: International Conference of the Italian Association for Artificial Intelligence
AIxIA 2021 – Advances in Artificial Intelligence ISBN: 9783031084201

In recent years, there have been many attempts to combine XAI with the field of symbolic AI in order to generate explanations for neural networks that are more interpretable and better align with human reasoning, with one prominent candidate for this

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ac5dff067b36c2958cbc15f1fc4c0219
http://hdl.handle.net/10044/1/99449