Readability is a fundamental problem in textbooks assessment.For low resources languages(LRL),however,little investigation has been done on the readability of textbook.In this paper,we proposed a readability assessmen...Readability is a fundamental problem in textbooks assessment.For low resources languages(LRL),however,little investigation has been done on the readability of textbook.In this paper,we proposed a readability assessment method for Tibetan textbook(a low resource language).We extract features based on the information that are gotten by Tibetan segmentation and named entity recognition.Then,we calculate the correlation of different features using Pearson Correlation Coefficient and select some feature sets to design the readability formula.Fit detection,F test and T test are applied on these selected features to generate a new readability assessment formula.Experiment shows that this new formula is capable of assessing the readability of Tibetan textbooks.展开更多
In the current era of multimedia information,it is increasingly urgent to realize intelligent video action recognition and content analysis.In the past few years,video action recognition,as an important direction in c...In the current era of multimedia information,it is increasingly urgent to realize intelligent video action recognition and content analysis.In the past few years,video action recognition,as an important direction in computer vision,has attracted many researchers and made much progress.First,this paper reviews the latest video action recognition methods based on Deep Neural Network and Markov Logic Network.Second,we analyze the characteristics of each method and the performance from the experiment results.Then compare the emphases of these methods and discuss the application scenarios.Finally,we consider and prospect the development trend and direction of this field.展开更多
A large number of nodule minerals exist in the deep sea.Based on the factors of difficulty in shooting,high economic cost and high accuracy of resource assessment,large-scale planned commercial mining has not yet been...A large number of nodule minerals exist in the deep sea.Based on the factors of difficulty in shooting,high economic cost and high accuracy of resource assessment,large-scale planned commercial mining has not yet been conducted.Only experimental mining has been carried out in areas with high mineral density and obvious benefits after mineral resource assessment.As an efficient method for deep-sea mineral resource assessment,the deep towing system is equipped with a visual system for mineral resource analysis using collected images and videos,which has become a key component of resource assessment.Therefore,high accuracy in deep-sea mineral image segmentation is the primary goal of the segmentation algorithm.In this paper,the existing deep-sea nodule mineral image segmentation algorithms are studied in depth and divided into traditional and deep learning-based segmentation methods,and the advantages and disadvantages of each are compared and summarized.The deep learning methods show great advantages in deep-sea mineral image segmentation,and there is a great improvement in segmentation accuracy and efficiency compared with the traditional methods.Then,the mineral image dataset and segmentation evaluation metrics are listed.Finally,possible future research topics and improvement measures are discussed for the reference of other researchers.展开更多
Deep-sea mineral image segmentation plays an important role in deep-sea mining and underwater mineral resource monitoring and evaluation.The application of artificial intelligence technology to deep-sea mining project...Deep-sea mineral image segmentation plays an important role in deep-sea mining and underwater mineral resource monitoring and evaluation.The application of artificial intelligence technology to deep-sea mining projects can effectively improve the quality and efficiency of mining.The existing deep learning-based underwater image segmentation algorithms have problems such as the accuracy rate is not high enough and the running time is slightly longer.In order to improve the segmentation performance of underwater mineral images,this paper uses the Pix2PixHD(Pixel to Pixel High Definition)algorithm based on Conditional Generative Adversarial Network(CGAN)to segment deep-sea mineral images.The model uses a coarse-to-fine generator composed of a global generation network and two local enhancement networks,and multiple multi-scale discriminators with same network structures but different input pictures to generate highquality images.The test results on the deep-sea mineral datasets show that the Pix2PixHD algorithm can identify more target minerals under certain other conditions.The evaluation index shows that the Pix2PixHD algorithm effectively improves the accuracy rate and the recall rate of deep-sea mineral image segmentation compared with the CGAN algorithm and the U-Net algorithm.It is important for expanding the application of deep learning techniques in the field of deep-sea exploration and mining.展开更多
Text summarization creates subset that represents the most important or relevant information in the original content,which effectively reduce information redundancy.Recently neural network method has achieved good res...Text summarization creates subset that represents the most important or relevant information in the original content,which effectively reduce information redundancy.Recently neural network method has achieved good results in the task of text summarization both in Chinese and English,but the research of text summarization in low-resource languages is still in the exploratory stage,especially in Tibetan.What’s more,there is no large-scale annotated corpus for text summarization.The lack of dataset severely limits the development of low-resource text summarization.In this case,unsupervised learning approaches are more appealing in low-resource languages as they do not require labeled data.In this paper,we propose an unsupervised graph-based Tibetan multi-document summarization method,which divides a large number of Tibetan news documents into topics and extracts the summarization of each topic.Summarization obtained by using traditional graph-based methods have high redundancy and the division of documents topics are not detailed enough.In terms of topic division,we adopt two level clustering methods converting original document into document-level and sentence-level graph,next we take both linguistic and deep representation into account and integrate external corpus into graph to obtain the sentence semantic clustering.Improve the shortcomings of the traditional K-Means clustering method and perform more detailed clustering of documents.Then model sentence clusters into graphs,finally remeasure sentence nodes based on the topic semantic information and the impact of topic features on sentences,higher topic relevance summary is extracted.In order to promote the development of Tibetan text summarization,and to meet the needs of relevant researchers for high-quality Tibetan text summarization datasets,this paper manually constructs a Tibetan summarization dataset and carries out relevant experiments.The experiment results show that our method can effectively improve the quality of summarization and our method is competitive to previous unsupervised methods.展开更多
Commonsense question answering(CQA)requires understanding and reasoning over QA context and related commonsense knowledge,such as a structured Knowledge Graph(KG).Existing studies combine language models and graph neu...Commonsense question answering(CQA)requires understanding and reasoning over QA context and related commonsense knowledge,such as a structured Knowledge Graph(KG).Existing studies combine language models and graph neural networks to model inference.However,traditional knowledge graph are mostly concept-based,ignoring direct path evidence necessary for accurate reasoning.In this paper,we propose MRGNN(Meta-path Reasoning Graph Neural Network),a novel model that comprehensively captures sequential semantic information from concepts and paths.In MRGNN,meta-paths are introduced as direct inference evidence and an original graph neural network is adopted to aggregate features from both concepts and paths simultaneously.We conduct sufficient experiments on the CommonsenceQA and OpenBookQA datasets,showing the effectiveness of MRGNN.Also,we conduct further ablation experiments and explain the reasoning behavior through the case study.展开更多
The dysbiosis of microbiome may have negative effects on a host phenotype.The microbes related to the host phenotype are regarded as microbial association signals.Recently,statistical methods based on microbiome-pheno...The dysbiosis of microbiome may have negative effects on a host phenotype.The microbes related to the host phenotype are regarded as microbial association signals.Recently,statistical methods based on microbiome-phenotype association tests have been extensively developed to detect these association signals.However,the currently available methods do not perform well to detect microbial association signals when dealing with diverse sparsity levels(i.e.,sparse,low sparse,non-sparse).Actually,the real association patterns related to different host phenotypes are not unique.Here,we propose a powerful and adaptive microbiome-based association test to detect microbial association signals with diverse sparsity levels,designated as MiATDS.In particular,we define probability degree to measure the associations between microbes and the host phenotype and introduce the adaptive weighted sum of powered score tests by considering both probability degree and phylogenetic information.We design numerous simulation experiments for the task of detecting association signals with diverse sparsity levels to prove the performance of the method.We find that type I error rates can be well-controlled and MiATDS shows superior efficiency on the power.By applying to real data analysis,MiATDS displays reliable practicability too.The R package is available at https://github.com/XiaoyunHuang33/MiATDS.展开更多
1 Introduction.Inspired by the impressive success of BERT[1]in various NLP applications,researchers have attempted to apply pretrained language models to information retrieval,and existing BERT-based retrieval models ...1 Introduction.Inspired by the impressive success of BERT[1]in various NLP applications,researchers have attempted to apply pretrained language models to information retrieval,and existing BERT-based retrieval models obtain improved performance on passage retrieval[2-4].Since BERT has the limitation that the maximum length of tokens is only 512,however,simply applying those models to the task of long document retrieval derives suboptimal results.展开更多
基金This work was supported by the China National Natural Science Foundation No.(61331013)the Young faculty scientific research ability promotion program of Minzu University of China.
文摘Readability is a fundamental problem in textbooks assessment.For low resources languages(LRL),however,little investigation has been done on the readability of textbook.In this paper,we proposed a readability assessment method for Tibetan textbook(a low resource language).We extract features based on the information that are gotten by Tibetan segmentation and named entity recognition.Then,we calculate the correlation of different features using Pearson Correlation Coefficient and select some feature sets to design the readability formula.Fit detection,F test and T test are applied on these selected features to generate a new readability assessment formula.Experiment shows that this new formula is capable of assessing the readability of Tibetan textbooks.
基金This work was supported in part by National Science Foundation Project of P.R.China(Grant Nos.61503424,61331013)。
文摘In the current era of multimedia information,it is increasingly urgent to realize intelligent video action recognition and content analysis.In the past few years,video action recognition,as an important direction in computer vision,has attracted many researchers and made much progress.First,this paper reviews the latest video action recognition methods based on Deep Neural Network and Markov Logic Network.Second,we analyze the characteristics of each method and the performance from the experiment results.Then compare the emphases of these methods and discuss the application scenarios.Finally,we consider and prospect the development trend and direction of this field.
基金This work was supported in part by the National Science Foundation Project of P.R.China under Grant No.52071349,No.U1906234partially supported by the Open Project Program of Key Laboratory ofMarine Environmental Survey Technology and Application,Ministry of Natural Resource MESTA-2020-B001+1 种基金Young and Middle-aged Talents Project of the State Ethnic Affairs Commission,the Crossdisciplinary Research Project of Minzu University of China(2020MDJC08)the Graduate Research and Practice Projects of Minzu University of China(SZKY2021039).
文摘A large number of nodule minerals exist in the deep sea.Based on the factors of difficulty in shooting,high economic cost and high accuracy of resource assessment,large-scale planned commercial mining has not yet been conducted.Only experimental mining has been carried out in areas with high mineral density and obvious benefits after mineral resource assessment.As an efficient method for deep-sea mineral resource assessment,the deep towing system is equipped with a visual system for mineral resource analysis using collected images and videos,which has become a key component of resource assessment.Therefore,high accuracy in deep-sea mineral image segmentation is the primary goal of the segmentation algorithm.In this paper,the existing deep-sea nodule mineral image segmentation algorithms are studied in depth and divided into traditional and deep learning-based segmentation methods,and the advantages and disadvantages of each are compared and summarized.The deep learning methods show great advantages in deep-sea mineral image segmentation,and there is a great improvement in segmentation accuracy and efficiency compared with the traditional methods.Then,the mineral image dataset and segmentation evaluation metrics are listed.Finally,possible future research topics and improvement measures are discussed for the reference of other researchers.
基金This work was supported in part by national science foundation project of P.R.China under Grant No.52071349,No.U1906234 Partially Supported by the Open Project Program of Key Laboratory of Marine Environmental Survey Technology and ApplicationMinistry of Natural Resource MESTA-2020-B001+1 种基金the cross discipline research project of Minzu University of China(2020MDJC08)the Graduate Research and Practice Projects of Minzu University of China.
文摘Deep-sea mineral image segmentation plays an important role in deep-sea mining and underwater mineral resource monitoring and evaluation.The application of artificial intelligence technology to deep-sea mining projects can effectively improve the quality and efficiency of mining.The existing deep learning-based underwater image segmentation algorithms have problems such as the accuracy rate is not high enough and the running time is slightly longer.In order to improve the segmentation performance of underwater mineral images,this paper uses the Pix2PixHD(Pixel to Pixel High Definition)algorithm based on Conditional Generative Adversarial Network(CGAN)to segment deep-sea mineral images.The model uses a coarse-to-fine generator composed of a global generation network and two local enhancement networks,and multiple multi-scale discriminators with same network structures but different input pictures to generate highquality images.The test results on the deep-sea mineral datasets show that the Pix2PixHD algorithm can identify more target minerals under certain other conditions.The evaluation index shows that the Pix2PixHD algorithm effectively improves the accuracy rate and the recall rate of deep-sea mineral image segmentation compared with the CGAN algorithm and the U-Net algorithm.It is important for expanding the application of deep learning techniques in the field of deep-sea exploration and mining.
基金This work was supported in part by the National Science Foundation Project of P.R.China 484 under Grant No.52071349partially supported by Young and Middle-aged Talents Project of the State Ethnic Affairs 487 Commission.
文摘Text summarization creates subset that represents the most important or relevant information in the original content,which effectively reduce information redundancy.Recently neural network method has achieved good results in the task of text summarization both in Chinese and English,but the research of text summarization in low-resource languages is still in the exploratory stage,especially in Tibetan.What’s more,there is no large-scale annotated corpus for text summarization.The lack of dataset severely limits the development of low-resource text summarization.In this case,unsupervised learning approaches are more appealing in low-resource languages as they do not require labeled data.In this paper,we propose an unsupervised graph-based Tibetan multi-document summarization method,which divides a large number of Tibetan news documents into topics and extracts the summarization of each topic.Summarization obtained by using traditional graph-based methods have high redundancy and the division of documents topics are not detailed enough.In terms of topic division,we adopt two level clustering methods converting original document into document-level and sentence-level graph,next we take both linguistic and deep representation into account and integrate external corpus into graph to obtain the sentence semantic clustering.Improve the shortcomings of the traditional K-Means clustering method and perform more detailed clustering of documents.Then model sentence clusters into graphs,finally remeasure sentence nodes based on the topic semantic information and the impact of topic features on sentences,higher topic relevance summary is extracted.In order to promote the development of Tibetan text summarization,and to meet the needs of relevant researchers for high-quality Tibetan text summarization datasets,this paper manually constructs a Tibetan summarization dataset and carries out relevant experiments.The experiment results show that our method can effectively improve the quality of summarization and our method is competitive to previous unsupervised methods.
基金supported by the Key Research and Development Program of Hubei Province(2020BAB017)the Scientific Research Center Program of National Language Commission(ZDI135-135)the Fundamental Research Funds for the Central Universities(KJ02502022-0155,CCNU22XJ037).
文摘Commonsense question answering(CQA)requires understanding and reasoning over QA context and related commonsense knowledge,such as a structured Knowledge Graph(KG).Existing studies combine language models and graph neural networks to model inference.However,traditional knowledge graph are mostly concept-based,ignoring direct path evidence necessary for accurate reasoning.In this paper,we propose MRGNN(Meta-path Reasoning Graph Neural Network),a novel model that comprehensively captures sequential semantic information from concepts and paths.In MRGNN,meta-paths are introduced as direct inference evidence and an original graph neural network is adopted to aggregate features from both concepts and paths simultaneously.We conduct sufficient experiments on the CommonsenceQA and OpenBookQA datasets,showing the effectiveness of MRGNN.Also,we conduct further ablation experiments and explain the reasoning behavior through the case study.
基金supported by the National Natural Science Foundation of China(61872157,61932008,61532008)the Key Research and Development Program of Hubei Province(2020BAB017)。
文摘The dysbiosis of microbiome may have negative effects on a host phenotype.The microbes related to the host phenotype are regarded as microbial association signals.Recently,statistical methods based on microbiome-phenotype association tests have been extensively developed to detect these association signals.However,the currently available methods do not perform well to detect microbial association signals when dealing with diverse sparsity levels(i.e.,sparse,low sparse,non-sparse).Actually,the real association patterns related to different host phenotypes are not unique.Here,we propose a powerful and adaptive microbiome-based association test to detect microbial association signals with diverse sparsity levels,designated as MiATDS.In particular,we define probability degree to measure the associations between microbes and the host phenotype and introduce the adaptive weighted sum of powered score tests by considering both probability degree and phylogenetic information.We design numerous simulation experiments for the task of detecting association signals with diverse sparsity levels to prove the performance of the method.We find that type I error rates can be well-controlled and MiATDS shows superior efficiency on the power.By applying to real data analysis,MiATDS displays reliable practicability too.The R package is available at https://github.com/XiaoyunHuang33/MiATDS.
基金supported by the Key Research and Development Program of Hubei Province(2020BAB017)Scientific Research Center Program of National Language Commission(ZDI135-135)the Fundamental Research Funds for the Central Universities(CCNU22QN015).
文摘1 Introduction.Inspired by the impressive success of BERT[1]in various NLP applications,researchers have attempted to apply pretrained language models to information retrieval,and existing BERT-based retrieval models obtain improved performance on passage retrieval[2-4].Since BERT has the limitation that the maximum length of tokens is only 512,however,simply applying those models to the task of long document retrieval derives suboptimal results.
