Background External knowledge representations play an essential role in knowledge-based visual question and answering to better understand complex scenarios in the open world.Recent entity-relationship embedding appro...Background External knowledge representations play an essential role in knowledge-based visual question and answering to better understand complex scenarios in the open world.Recent entity-relationship embedding approaches are deficient in representing some complex relations,resulting in a lack of topic-related knowledge and redundancy in topic-irrelevant information.Methods To this end,we propose MKEAH:Multimodal Knowledge Extraction and Accumulation on Hyperplanes.To ensure that the lengths of the feature vectors projected onto the hyperplane compare equally and to filter out sufficient topic-irrelevant information,two losses are proposed to learn the triplet representations from the complementary views:range loss and orthogonal loss.To interpret the capability of extracting topic-related knowledge,we present the Topic Similarity(TS)between topic and entity-relations.Results Experimental results demonstrate the effectiveness of hyperplane embedding for knowledge representation in knowledge-based visual question answering.Our model outperformed state-of-the-art methods by 2.12%and 3.24%on two challenging knowledge-request datasets:OK-VQA and KRVQA,respectively.Conclusions The obvious advantages of our model in TS show that using hyperplane embedding to represent multimodal knowledge can improve its ability to extract topic-related knowledge.展开更多
Fluency on oral English has always been the goal of Chinese English learners. Language corpuses offer great convenience to language researches. Prefabricated chunks are a great help for learners to achieve oral Englis...Fluency on oral English has always been the goal of Chinese English learners. Language corpuses offer great convenience to language researches. Prefabricated chunks are a great help for learners to achieve oral English fluency. With the help of computer software, chunks in SECCL are categorized. The conclusion is in the process of chunks acquiring, emphasis should be on content-related chunks, especially specific topic-related ones. One effective way to gain topic-related chunks is to build topic-related English corpus of native speakers.展开更多
为了提高文本标记和分类的效率,提出了基于概念语义相关性和LDA的文本自动标记算法(Text Mark Label,TML),用以代替人工标记的文本分类标记.该算法在概念语义相关性计算的基础上,使用LDA(Latent Dirichlet Allocation)提取文本的主题表...为了提高文本标记和分类的效率,提出了基于概念语义相关性和LDA的文本自动标记算法(Text Mark Label,TML),用以代替人工标记的文本分类标记.该算法在概念语义相关性计算的基础上,使用LDA(Latent Dirichlet Allocation)提取文本的主题表示,通过计算文本主题从属于各分类目录的期望从而实现文本自动标记.为验证TML算法的效果,在标准文本分类数据集上使用文本分类器进行有监督文本分类实验.为对比数据集和分类器对分类效果的影响,在3个数据集(WebKB、Reuters-21578、20-News Group)上分别使用3种不同的分类器(Rocchio、KNN、SVM)进行实验.实验结果表明:TML算法有效地提高了文本分类效率及文本标记效率.展开更多
基金Supported by National Nature Science Foudation of China(61976160,61906137,61976158,62076184,62076182)Shanghai Science and Technology Plan Project(21DZ1204800)。
文摘Background External knowledge representations play an essential role in knowledge-based visual question and answering to better understand complex scenarios in the open world.Recent entity-relationship embedding approaches are deficient in representing some complex relations,resulting in a lack of topic-related knowledge and redundancy in topic-irrelevant information.Methods To this end,we propose MKEAH:Multimodal Knowledge Extraction and Accumulation on Hyperplanes.To ensure that the lengths of the feature vectors projected onto the hyperplane compare equally and to filter out sufficient topic-irrelevant information,two losses are proposed to learn the triplet representations from the complementary views:range loss and orthogonal loss.To interpret the capability of extracting topic-related knowledge,we present the Topic Similarity(TS)between topic and entity-relations.Results Experimental results demonstrate the effectiveness of hyperplane embedding for knowledge representation in knowledge-based visual question answering.Our model outperformed state-of-the-art methods by 2.12%and 3.24%on two challenging knowledge-request datasets:OK-VQA and KRVQA,respectively.Conclusions The obvious advantages of our model in TS show that using hyperplane embedding to represent multimodal knowledge can improve its ability to extract topic-related knowledge.
文摘Fluency on oral English has always been the goal of Chinese English learners. Language corpuses offer great convenience to language researches. Prefabricated chunks are a great help for learners to achieve oral English fluency. With the help of computer software, chunks in SECCL are categorized. The conclusion is in the process of chunks acquiring, emphasis should be on content-related chunks, especially specific topic-related ones. One effective way to gain topic-related chunks is to build topic-related English corpus of native speakers.