Existing abstractive summarization methods only focus on the correlation between the original words and the summary words, ignoring the topics’ influence on the summaries. To this end, an abstract summarization method combining global topic information, ACGT, is proposed. A topic information extractor, based on Latent Dirichlet Allocation, is constructed to extract key topic information from the original text, and an attention module is built to fuse key topic information with the original text representation. The summary is then generated by combining a pointer generation network and coverage mechanism. With evaluation metrics of ROUGE-1, ROUGE-2, and ROUGE-L, the experimental results of ACGT in the English dataset CNN/Daily Mail are 0.96%, 2.44%, and 1.03% higher than the baseline model, respectively. In the Chinese dataset, LCSTS, ACGT shows a higher performance than the baseline method by 1.19%, 1.03%, and 0.85%, respectively. Our results demonstrate that the performance of summaries is significantly correlated with the number of topics that are introduced. Case studies show that the introduction of topic information can improve both the coverage of original text topics and the fluency of summaries.
16 February 2025 in CAAI Transactions on Intelligence Technology
Existing Chinese named entity recognition (NER) research utilises 1D lexicon‐based sequence labelling frameworks, which can only recognise flat entities. While lexicons serve as prior knowledge and enhance semantic information, they also pose completeness and resource requirements limitations. This paper proposes a template‐based classification (TC) model to avoid lexicon issues and to identify nested entities. Template‐based classification provides a template word for each entity type, which utilises contrastive learning to integrate the common characteristics among entities with the same category. Contrastive learning makes template words the centre points of their category in the vector space, thus improving generalisation ability. Additionally, TC presents a 2D table‐filling label scheme that classifies entities based on the attention distribution of template words. The proposed novel decoder algorithm enables TC recognition of both flat and nested entities simultaneously. Experimental results show that TC achieves the state‐of‐the‐art performance on five Chinese datasets.
In order to improve the localization accuracy of edges, an edge detector is proposed for synthetic aperture radar (SAR) images. The proposed detector, named as C-RBED, combines the Canny detector with the ratio-based edge detector (RBED). The proposed detector shows almost unbiased localization accuracy for the edges in SAR images, which benefits from the unbiased localization ability of Canny. On the other hand, C-RBED keeps the property of the constant false alarm rate as the result of RBED component. C-RBED obviously improves the localization accuracy of edges and hence achieves a high true positive detection rate. The experimental results on both simulated and real-world SAR images show that C-RBED can achieve better performance than traditional SAR edge detection methods in the sense of localization accuracy and edge continuity.