In the era of Big Data,we are faced with an inevitable and challenging problem of“overload information”.To alleviate this problem,it is important to use effective automatic text summarization techniques to obtain th...In the era of Big Data,we are faced with an inevitable and challenging problem of“overload information”.To alleviate this problem,it is important to use effective automatic text summarization techniques to obtain the key information quickly and efficiently from the huge amount of text.In this paper,we propose a hybrid method of extractive text summarization based on deep learning and graph ranking algorithms(ETSDG).In this method,a pre-trained deep learning model is designed to yield useful sentence embeddings.Given the association between sentences in raw documents,a traditional LexRank algorithm with fine-tuning is adopted fin ETSDG.In order to improve the performance of the extractive text summarization method,we further integrate the traditional LexRank algorithm with deep learning.Testing results on the data set DUC2004 show that ETSDG has better performance in ROUGE metrics compared with certain benchmark methods.展开更多
High-resolution bathymetric side-scan sonar(BSSS) performs the functions of traditional side-scan sonar, while also providing a depth-sounding function that allows simultaneous measurement of seafloor topography and g...High-resolution bathymetric side-scan sonar(BSSS) performs the functions of traditional side-scan sonar, while also providing a depth-sounding function that allows simultaneous measurement of seafloor topography and geomorphology. Submarine microtopography and microgeomorphology detection ability and advanced underwater acoustic digital communication are important technical capabilities of the Jiaolong manned submersible. High resolution BSSS achieved accurate detection of seafloor topography and geomorphology at a depth of 7000 m, and successful mapping of local microtopography and microgeomorphology in the Mariana Trench.展开更多
文摘In the era of Big Data,we are faced with an inevitable and challenging problem of“overload information”.To alleviate this problem,it is important to use effective automatic text summarization techniques to obtain the key information quickly and efficiently from the huge amount of text.In this paper,we propose a hybrid method of extractive text summarization based on deep learning and graph ranking algorithms(ETSDG).In this method,a pre-trained deep learning model is designed to yield useful sentence embeddings.Given the association between sentences in raw documents,a traditional LexRank algorithm with fine-tuning is adopted fin ETSDG.In order to improve the performance of the extractive text summarization method,we further integrate the traditional LexRank algorithm with deep learning.Testing results on the data set DUC2004 show that ETSDG has better performance in ROUGE metrics compared with certain benchmark methods.
基金supported by the National Key R&D Program of China (Grant No. 2017YFC0305700)the Qingdao National Laboratory for Marine Science and Technology (Grant No. QNLM2016ORP0406)+4 种基金the National Natural Science Foundation of China (Grant No. 41641049)the Taishan Scholar Project Funding (Grant No. TSPD20161007)the Shandong Provincial Natural Science Foundation (Grant No. ZR2015EM005)the Shandong Provincial Key R&D Program (Grant No. 2016GSF115006)the Qingdao Independent Innovation Project (Grant No. 15-9-1-90-JCH)
文摘High-resolution bathymetric side-scan sonar(BSSS) performs the functions of traditional side-scan sonar, while also providing a depth-sounding function that allows simultaneous measurement of seafloor topography and geomorphology. Submarine microtopography and microgeomorphology detection ability and advanced underwater acoustic digital communication are important technical capabilities of the Jiaolong manned submersible. High resolution BSSS achieved accurate detection of seafloor topography and geomorphology at a depth of 7000 m, and successful mapping of local microtopography and microgeomorphology in the Mariana Trench.
