A group of students, including two first authors Vo Song Nguyen and Vo Tien Thinh (alumni of the  Program, class of 2019, Faculty of Information Technology), has just published the paper "Interpretable extractive text summarization with meta-learning and BI-LSTM: A study of meta-learning and explainability techniques" in Expert Systems with Applications (SCIE-Q1, IF 8.5). This work was done under the supervision of Prof. Dr. Le Hoai Bac (Head of the Department of Computer Science).

⭐️ Research highlights: The paper introduces a novel approach for extractive text summarization in natural language processing (NLP) using meta-learning and BI-LSTM. The effectiveness is compared with top NLP models via ROUGE metrics.

 Paper link: https://doi.org/10.1016/j.eswa.2023.123045 

✅ Paper abstract: Text summarization is a widely-researched problem among scholars in the field of natural language processing. Multiple techniques have been proposed to help tackle this problem, yet some of these methodologies may still exhibit limitations such as the requirements for large training datasets, which might not always be possible, but more importantly, the lack of interpretability or transparency of the model. In this paper, we propose using meta-learning algorithm to train a deep learning model for extractive text summarization and then using various explanatory techniques such as SHAP (Shapley, 1953), linear regression (Lederer, 2022), decision trees (Fürnkranz, 2010), and input modification to gain insights into the model’s decision making process. To evaluate the effectiveness of our approach, we will compare it to other popular natural language processing models like BERT (Miller, 2019) or XLNET (Yang et al., 2020) using the ROUGE metrics (Lin, 2004). Overall, our proposed approach provides a promising solution to the limitations of existing methods and a framework for improving the explainability of deep learning models in other natural language processing tasks.