Search

Pretrained models in abstractive summarization enable the summarization model to generate coherent summaries flexibly, but it also introduces unfactual hallucinations when generating novel words. To circumvent this drawback, we propose A Guided Tensor Product framework for abstractive Summarization (GTPSum). GTPSum utilizes highlighted sentence guidance signal and role embedding in the form of guided tensor product representations (GTPRs) to enhance the generation capacity for short document text. The guidance signal assists the model in focusing on crucial information, while the role embedding aids GTPSum in capturing the syntactic structure relationships present in the sentences. By employing this approach, the framework can not only focus on the essential information from the source document but also grasp the inherent sentence structure, resulting in generated summaries that closely align with the original content. The experimental results demonstrate the strong performance of our approach on the CNN/Daily Mail (44.28/20.88/41.08 ROUGE-1/-2/-L) and performed well on the other three datasets. Moreover, the comparison between our model generated summaries and those generated by the baseline models through human evaluation shows that our summaries contain more critical information, have better readability, and still maintain succinctness. [ABSTRACT FROM AUTHOR]

Recently, drilling wells have encountered rich gas hydrates in fine-grained sediments in the northern South China Sea. Gas hydrate in fine-grained sediments is very heterogeneous, and its physical properties are different from those of oil and gas reservoirs. The reliability of the classical logging saturation evaluation models established for diagenetic reservoirs is questionable. This study used four wells in GMGS3 and GMGS4 to evaluate the effects of the application of three typical methods for evaluating saturation with different principles in the unconsolidated fine-grained sediments: nuclear magnetic logging, sigma logging, and the Archie formula. It was found that the value of the lithologic capture cross-section in sigma logging and the rock's electrical parameters in the Archie formula affect the accuracy of the model. Therefore, to obtain a reliable saturation value for fine-grained sediments, an innovative method for the calculation of resistivity and acoustic time is proposed to estimate gas hydrate saturation based on logging data, which is most consistent with the results of core analysis. The overall relative error of the verification well was 5.87%, whereas that of the density NMR logging method was 56%, showing that the accuracy of the newly proposed resistivity DT logging method's saturation formula was significantly improved. Finally, a new model-based cross chart was developed, which can rapidly differentiate gas saturation during drilling. [ABSTRACT FROM AUTHOR]