Publications

Enhancing Abstractive Summarization of Scientific Papers Using Structure Information

Published in Expert system with application, 2024

Abstractive summarization of scientific papers has always been a research focus. yet existing methods face two main challenges. First, most summarization models rely on Encoder-Decoder architectures that treat papers as sequences of words, thus fail to fully capture the structured information inherent in scientific papers. Second, existing research often use keyword mapping or feature engineering to identify the structural information, but these methods struggle with the structural flexibility of scientific papers and lack robustness across different disciplines. To address these challenges, we propose a two-stage abstractive summarization framework that leverages automatic recognition of structural functions within scientific papers. In the first stage, we standardize chapter titles from numerous scientific papers and construct a large-scale dataset for structural function recognition. A classifier is then trained to automatically identify the key structural components (e.g., Background, Methods, Results, Discussion), which provides a foundation for generating more balanced summaries. In the second stage, we employ Longformer to capture rich contextual relationships across sections and generating context-aware summaries. Experiments conducted on two domain-specific scientific paper summarization datasets demonstrate that our method outperforms advanced baselines, and generates more comprehensive summaries.

Recommended citation: Tong Bao, Heng Zhang, Chengzhi Zhang*. Enhancing Abstractive Summarization of Scientific Papers based on Structure Information. Expert system with application, 2024.

A BERT-Based Hybrid Short Text Classification Model Incorporating CNN and Attention-Based BiGRU

Published in Journal of Organizational and End User Computing(Volume 33,6), 2021

Short text classification is a research focus for natural language processing (NLP), which is widely used in news classification, sentiment analysis, mail filtering, and other fields. In recent years, deep learning techniques are applied to text classification and have made some progress. Different from ordinary text classification, short text has the problem of less vocabulary and feature sparsity, which raise higher request for text semantic feature representation. To address this issue, this paper proposes a feature fusion framework based on the bidirectional encoder representations from transformers (BERT). In this hybrid method, BERT is used to train word vector representation. Convolutional neural network (CNN) captures static features. As a supplement, a bi-gated recurrent neural network (BiGRU) is adopted to capture contextual features. Furthermore, an attention mechanism is introduced to assign the weight of salient words. The experimental results confirmed that the proposed model significantly outperforms the other state-of-the-art baseline methods.

Recommended citation: Bao, T., Ren, N., Luo, R., Wang, B., Shen, G., & Guo, T. (2021). A BERT-Based Hybrid Short Text Classification Model Incorporating CNN and Attention-Based BiGRU. Journal of Organizational and End User Computing (JOEUC), 33(6), 1-21. http://doi.org/10.4018/JOEUC.294580.