With the help of pre-trained language models,the accuracy of the entity linking task has made great strides in recent years.However,most models with excellent performance require fine-tuning on a large amount of train...With the help of pre-trained language models,the accuracy of the entity linking task has made great strides in recent years.However,most models with excellent performance require fine-tuning on a large amount of training data using large pre-trained language models,which is a hardware threshold to accomplish this task.Some researchers have achieved competitive results with less training data through ingenious methods,such as utilizing information provided by the named entity recognition model.This paper presents a novel semantic-enhancement-based entity linking approach,named semantically enhanced hardware-friendly entity linking(SHEL),which is designed to be hardware friendly and efficient while maintaining good performance.Specifically,SHEL's semantic enhancement approach consists of three aspects:(1)semantic compression of entity descriptions using a text summarization model;(2)maximizing the capture of mention contexts using asymmetric heuristics;(3)calculating a fixed size mention representation through pooling operations.These series of semantic enhancement methods effectively improve the model's ability to capture semantic information while taking into account the hardware constraints,and significantly improve the model's convergence speed by more than 50%compared with the strong baseline model proposed in this paper.In terms of performance,SHEL is comparable to the previous method,with superior performance on six well-established datasets,even though SHEL is trained using a smaller pre-trained language model as the encoder.展开更多
As the research of knowledge graph(KG)is deepened and widely used,knowledge graph com-pletion(KGC)has attracted more and more attentions from researchers,especially in scenarios of in-telligent search,social networks ...As the research of knowledge graph(KG)is deepened and widely used,knowledge graph com-pletion(KGC)has attracted more and more attentions from researchers,especially in scenarios of in-telligent search,social networks and deep question and answer(Q&A).Current research mainly fo-cuses on the completion of static knowledge graphs,and the temporal information in temporal knowl-edge graphs(TKGs)is ignored.However,the temporal information is definitely very helpful for the completion.Note that existing researches on temporal knowledge graph completion are difficult to process temporal information and to integrate entities,relations and time well.In this work,a rotation and scaling(RotatS)model is proposed,which learns rotation and scaling transformations from head entity embedding to tail entity embedding in 3D spaces to capture the information of time and rela-tions in the temporal knowledge graph.The performance of the proposed RotatS model have been evaluated by comparison with several baselines under similar experimental conditions and space com-plexity on four typical knowl good graph completion datasets publicly available online.The study shows that RotatS can achieve good results in terms of prediction accuracy.展开更多
Knowledge graph(KG) link prediction aims to address the problem of missing multiple valid triples in KGs. Existing approaches either struggle to efficiently model the message passing process of multi-hop paths or lack...Knowledge graph(KG) link prediction aims to address the problem of missing multiple valid triples in KGs. Existing approaches either struggle to efficiently model the message passing process of multi-hop paths or lack transparency of model prediction principles. In this paper,a new graph convolutional network path semantic-aware graph convolution network(PSGCN) is proposed to achieve modeling the semantic information of multi-hop paths. PSGCN first uses a random walk strategy to obtain all-hop paths in KGs,then captures the semantics of the paths by Word2Sec and long shortterm memory(LSTM) models,and finally converts them into a potential representation for the graph convolution network(GCN) messaging process. PSGCN combines path-based inference methods and graph neural networks to achieve better interpretability and scalability. In addition,to ensure the robustness of the model,the value of the path thresholdKis experimented on the FB15K-237 and WN18RR datasets,and the final results prove the effectiveness of the model.展开更多
To solve the problem of missing many valid triples in knowledge graphs(KGs),a novel model based on a convolutional neural network(CNN)called ConvKG is proposed,which employs a joint learning strategy for knowledge gra...To solve the problem of missing many valid triples in knowledge graphs(KGs),a novel model based on a convolutional neural network(CNN)called ConvKG is proposed,which employs a joint learning strategy for knowledge graph completion(KGC).Related research work has shown the superiority of convolutional neural networks(CNNs)in extracting semantic features of triple embeddings.However,these researches use only one single-shaped filter and fail to extract semantic features of different granularity.To solve this problem,ConvKG exploits multi-shaped filters to co-convolute on the triple embeddings,joint learning semantic features of different granularity.Different shaped filters cover different sizes on the triple embeddings and capture pairwise interactions of different granularity among triple elements.Experimental results confirm the strength of joint learning,and compared with state-of-the-art CNN-based KGC models,ConvKG achieves the better mean rank(MR)and Hits@10 metrics on dataset WN18 RR,and the better MR on dataset FB15k-237.展开更多
The research on named entity recognition for label-few domain is becoming increasingly important.In this paper,a novel algorithm,positive unlabeled named entity recognition(PUNER)with multi-granularity language inform...The research on named entity recognition for label-few domain is becoming increasingly important.In this paper,a novel algorithm,positive unlabeled named entity recognition(PUNER)with multi-granularity language information,is proposed,which combines positive unlabeled(PU)learning and deep learning to obtain the multi-granularity language information from a few labeled in-stances and many unlabeled instances to recognize named entities.First,PUNER selects reliable negative instances from unlabeled datasets,uses positive instances and a corresponding number of negative instances to train the PU learning classifier,and iterates continuously to label all unlabeled instances.Second,a neural network-based architecture to implement the PU learning classifier is used,and comprehensive text semantics through multi-granular language information are obtained,which helps the classifier correctly recognize named entities.Performance tests of the PUNER are carried out on three multilingual NER datasets,which are CoNLL2003,CoNLL 2002 and SIGHAN Bakeoff 2006.Experimental results demonstrate the effectiveness of the proposed PUNER.展开更多
Graph embedding aims to map the high-dimensional nodes to a low-dimensional space and learns the graph relationship from its latent representations.Most existing graph embedding methods focus on the topological struct...Graph embedding aims to map the high-dimensional nodes to a low-dimensional space and learns the graph relationship from its latent representations.Most existing graph embedding methods focus on the topological structure of graph data,but ignore the semantic information of graph data,which results in the unsatisfied performance in practical applications.To overcome the problem,this paper proposes a novel deep convolutional adversarial graph autoencoder(GAE)model.To embed the semantic information between nodes in the graph data,the random walk strategy is first used to construct the positive pointwise mutual information(PPMI)matrix,then,graph convolutional net-work(GCN)is employed to encode the PPMI matrix and node content into the latent representation.Finally,the learned latent representation is used to reconstruct the topological structure of the graph data by decoder.Furthermore,the deep convolutional adversarial training algorithm is introduced to make the learned latent representation conform to the prior distribution better.The state-of-the-art experimental results on the graph data validate the effectiveness of the proposed model in the link prediction,node clustering and graph visualization tasks for three standard datasets,Cora,Citeseer and Pubmed.展开更多
在命名实体识别任务中,运用词典匹配的方法能够添加丰富的文本特征,但匹配到的词组信息多使用静态归一化的方法,缺乏自动推理能力。提出了基于动态词典匹配的语义增强中文命名实体识别方法。对输入句子中的字符,在词典中进行动态词组匹...在命名实体识别任务中,运用词典匹配的方法能够添加丰富的文本特征,但匹配到的词组信息多使用静态归一化的方法,缺乏自动推理能力。提出了基于动态词典匹配的语义增强中文命名实体识别方法。对输入句子中的字符,在词典中进行动态词组匹配,利用神经网络对词组加权,结合word2vec与ALBERT得到字符的增强特征表示;在序列建模层运用BiLSTM对字符的word2vec向量与字符增强特征进行模型训练;在标签推理层运用条件随机场(Conditional Random Field,CRF)识别命名实体。在中文Resume和Weibo数据集上进行实验,验证结果表明,该方法比传统方法具有更好的效果。展开更多
基金the Beijing Municipal Science and Technology Program(Z231100001323004)。
文摘With the help of pre-trained language models,the accuracy of the entity linking task has made great strides in recent years.However,most models with excellent performance require fine-tuning on a large amount of training data using large pre-trained language models,which is a hardware threshold to accomplish this task.Some researchers have achieved competitive results with less training data through ingenious methods,such as utilizing information provided by the named entity recognition model.This paper presents a novel semantic-enhancement-based entity linking approach,named semantically enhanced hardware-friendly entity linking(SHEL),which is designed to be hardware friendly and efficient while maintaining good performance.Specifically,SHEL's semantic enhancement approach consists of three aspects:(1)semantic compression of entity descriptions using a text summarization model;(2)maximizing the capture of mention contexts using asymmetric heuristics;(3)calculating a fixed size mention representation through pooling operations.These series of semantic enhancement methods effectively improve the model's ability to capture semantic information while taking into account the hardware constraints,and significantly improve the model's convergence speed by more than 50%compared with the strong baseline model proposed in this paper.In terms of performance,SHEL is comparable to the previous method,with superior performance on six well-established datasets,even though SHEL is trained using a smaller pre-trained language model as the encoder.
基金the National Natural Science Foundation of China(No.6187022153).
文摘As the research of knowledge graph(KG)is deepened and widely used,knowledge graph com-pletion(KGC)has attracted more and more attentions from researchers,especially in scenarios of in-telligent search,social networks and deep question and answer(Q&A).Current research mainly fo-cuses on the completion of static knowledge graphs,and the temporal information in temporal knowl-edge graphs(TKGs)is ignored.However,the temporal information is definitely very helpful for the completion.Note that existing researches on temporal knowledge graph completion are difficult to process temporal information and to integrate entities,relations and time well.In this work,a rotation and scaling(RotatS)model is proposed,which learns rotation and scaling transformations from head entity embedding to tail entity embedding in 3D spaces to capture the information of time and rela-tions in the temporal knowledge graph.The performance of the proposed RotatS model have been evaluated by comparison with several baselines under similar experimental conditions and space com-plexity on four typical knowl good graph completion datasets publicly available online.The study shows that RotatS can achieve good results in terms of prediction accuracy.
基金Supported by the National Natural Science Foundation of China(No.61876144).
文摘Knowledge graph(KG) link prediction aims to address the problem of missing multiple valid triples in KGs. Existing approaches either struggle to efficiently model the message passing process of multi-hop paths or lack transparency of model prediction principles. In this paper,a new graph convolutional network path semantic-aware graph convolution network(PSGCN) is proposed to achieve modeling the semantic information of multi-hop paths. PSGCN first uses a random walk strategy to obtain all-hop paths in KGs,then captures the semantics of the paths by Word2Sec and long shortterm memory(LSTM) models,and finally converts them into a potential representation for the graph convolution network(GCN) messaging process. PSGCN combines path-based inference methods and graph neural networks to achieve better interpretability and scalability. In addition,to ensure the robustness of the model,the value of the path thresholdKis experimented on the FB15K-237 and WN18RR datasets,and the final results prove the effectiveness of the model.
基金Supported by the National Natural Science Foundation of China(No.61876144)。
文摘To solve the problem of missing many valid triples in knowledge graphs(KGs),a novel model based on a convolutional neural network(CNN)called ConvKG is proposed,which employs a joint learning strategy for knowledge graph completion(KGC).Related research work has shown the superiority of convolutional neural networks(CNNs)in extracting semantic features of triple embeddings.However,these researches use only one single-shaped filter and fail to extract semantic features of different granularity.To solve this problem,ConvKG exploits multi-shaped filters to co-convolute on the triple embeddings,joint learning semantic features of different granularity.Different shaped filters cover different sizes on the triple embeddings and capture pairwise interactions of different granularity among triple elements.Experimental results confirm the strength of joint learning,and compared with state-of-the-art CNN-based KGC models,ConvKG achieves the better mean rank(MR)and Hits@10 metrics on dataset WN18 RR,and the better MR on dataset FB15k-237.
基金the National Natural Science Foundation of China(No.61876144)the Strategy Priority Research Program of Chinese Acade-my of Sciences(No.XDC02070600).
文摘The research on named entity recognition for label-few domain is becoming increasingly important.In this paper,a novel algorithm,positive unlabeled named entity recognition(PUNER)with multi-granularity language information,is proposed,which combines positive unlabeled(PU)learning and deep learning to obtain the multi-granularity language information from a few labeled in-stances and many unlabeled instances to recognize named entities.First,PUNER selects reliable negative instances from unlabeled datasets,uses positive instances and a corresponding number of negative instances to train the PU learning classifier,and iterates continuously to label all unlabeled instances.Second,a neural network-based architecture to implement the PU learning classifier is used,and comprehensive text semantics through multi-granular language information are obtained,which helps the classifier correctly recognize named entities.Performance tests of the PUNER are carried out on three multilingual NER datasets,which are CoNLL2003,CoNLL 2002 and SIGHAN Bakeoff 2006.Experimental results demonstrate the effectiveness of the proposed PUNER.
基金Supported by the Strategy Priority Research Program of Chinese Academy of Sciences(No.XDC02070600).
文摘Graph embedding aims to map the high-dimensional nodes to a low-dimensional space and learns the graph relationship from its latent representations.Most existing graph embedding methods focus on the topological structure of graph data,but ignore the semantic information of graph data,which results in the unsatisfied performance in practical applications.To overcome the problem,this paper proposes a novel deep convolutional adversarial graph autoencoder(GAE)model.To embed the semantic information between nodes in the graph data,the random walk strategy is first used to construct the positive pointwise mutual information(PPMI)matrix,then,graph convolutional net-work(GCN)is employed to encode the PPMI matrix and node content into the latent representation.Finally,the learned latent representation is used to reconstruct the topological structure of the graph data by decoder.Furthermore,the deep convolutional adversarial training algorithm is introduced to make the learned latent representation conform to the prior distribution better.The state-of-the-art experimental results on the graph data validate the effectiveness of the proposed model in the link prediction,node clustering and graph visualization tasks for three standard datasets,Cora,Citeseer and Pubmed.
文摘在命名实体识别任务中,运用词典匹配的方法能够添加丰富的文本特征,但匹配到的词组信息多使用静态归一化的方法,缺乏自动推理能力。提出了基于动态词典匹配的语义增强中文命名实体识别方法。对输入句子中的字符,在词典中进行动态词组匹配,利用神经网络对词组加权,结合word2vec与ALBERT得到字符的增强特征表示;在序列建模层运用BiLSTM对字符的word2vec向量与字符增强特征进行模型训练;在标签推理层运用条件随机场(Conditional Random Field,CRF)识别命名实体。在中文Resume和Weibo数据集上进行实验,验证结果表明,该方法比传统方法具有更好的效果。
