Statistics released by China Customs in February,2007 showed an uncommon rapid growth in Shenzhen’s 2006 textile export.In 2006,the total value of textile
China's central bank in October announced plans to expand a pilot program on credit assets to nine municipalities and provinces, allowing banks to pledge assets to borrow from the central bank. In August, China's to...China's central bank in October announced plans to expand a pilot program on credit assets to nine municipalities and provinces, allowing banks to pledge assets to borrow from the central bank. In August, China's top legislature adopted an amendment to the law on commercial banks, removing the 7S-percent loan- to-deposit ratio stipulation. Both measures have been interpreted by some financial institutions as a stimulus of 7 trillion yuan ($1.11 trillion) and a "Chinese- style quantitative easing (QE)" policy. In a recent article in the National Business Daily, chief bond analyst of Minsheng Securities Co. Ltd., believes that such judgment lacks logic. Edited excerpts of the article follow.展开更多
In the field of natural language processing(NLP),there have been various pre-training language models in recent years,with question answering systems gaining significant attention.However,as algorithms,data,and comput...In the field of natural language processing(NLP),there have been various pre-training language models in recent years,with question answering systems gaining significant attention.However,as algorithms,data,and computing power advance,the issue of increasingly larger models and a growing number of parameters has surfaced.Consequently,model training has become more costly and less efficient.To enhance the efficiency and accuracy of the training process while reducing themodel volume,this paper proposes a first-order pruningmodel PAL-BERT based on the ALBERT model according to the characteristics of question-answering(QA)system and language model.Firstly,a first-order network pruning method based on the ALBERT model is designed,and the PAL-BERT model is formed.Then,the parameter optimization strategy of the PAL-BERT model is formulated,and the Mish function was used as an activation function instead of ReLU to improve the performance.Finally,after comparison experiments with traditional deep learning models TextCNN and BiLSTM,it is confirmed that PALBERT is a pruning model compression method that can significantly reduce training time and optimize training efficiency.Compared with traditional models,PAL-BERT significantly improves the NLP task’s performance.展开更多
Approximately 50%-70%of patients with hepatocellular carcinoma experience recurrence within five years after curative hepatic resection or ablation.As a result,many patients receive adjuvant therapy after curative res...Approximately 50%-70%of patients with hepatocellular carcinoma experience recurrence within five years after curative hepatic resection or ablation.As a result,many patients receive adjuvant therapy after curative resection or ablation in order to prolong recurrence-free survival.The therapy recommended by national guidelines can differ,and guidelines do not specify when to initiate adjuvant therapy or how long to continue it.These and other unanswered questions around adjuvant therapies make it difficult to optimize them and determine which may be more appropriate for a given type of patient.These questions need to be addressed by clinicians and researchers.展开更多
The weapon and equipment operational requirement analysis(WEORA) is a necessary condition to win a future war,among which the acquisition of knowledge about weapons and equipment is a great challenge. The main challen...The weapon and equipment operational requirement analysis(WEORA) is a necessary condition to win a future war,among which the acquisition of knowledge about weapons and equipment is a great challenge. The main challenge is that the existing weapons and equipment data fails to carry out structured knowledge representation, and knowledge navigation based on natural language cannot efficiently support the WEORA. To solve above problem, this research proposes a method based on question answering(QA) of weapons and equipment knowledge graph(WEKG) to construct and navigate the knowledge related to weapons and equipment in the WEORA. This method firstly constructs the WEKG, and builds a neutral network-based QA system over the WEKG by means of semantic parsing for knowledge navigation. Finally, the method is evaluated and a chatbot on the QA system is developed for the WEORA. Our proposed method has good performance in the accuracy and efficiency of searching target knowledge, and can well assist the WEORA.展开更多
Visual Question Answering(VQA)has sparked widespread interest as a crucial task in integrating vision and language.VQA primarily uses attention mechanisms to effectively answer questions to associate relevant visual r...Visual Question Answering(VQA)has sparked widespread interest as a crucial task in integrating vision and language.VQA primarily uses attention mechanisms to effectively answer questions to associate relevant visual regions with input questions.The detection-based features extracted by the object detection network aim to acquire the visual attention distribution on a predetermined detection frame and provide object-level insights to answer questions about foreground objects more effectively.However,it cannot answer the question about the background forms without detection boxes due to the lack of fine-grained details,which is the advantage of grid-based features.In this paper,we propose a Dual-Level Feature Embedding(DLFE)network,which effectively integrates grid-based and detection-based image features in a unified architecture to realize the complementary advantages of both features.Specifically,in DLFE,In DLFE,firstly,a novel Dual-Level Self-Attention(DLSA)modular is proposed to mine the intrinsic properties of the two features,where Positional Relation Attention(PRA)is designed to model the position information.Then,we propose a Feature Fusion Attention(FFA)to address the semantic noise caused by the fusion of two features and construct an alignment graph to enhance and align the grid and detection features.Finally,we use co-attention to learn the interactive features of the image and question and answer questions more accurately.Our method has significantly improved compared to the baseline,increasing accuracy from 66.01%to 70.63%on the test-std dataset of VQA 1.0 and from 66.24%to 70.91%for the test-std dataset of VQA 2.0.展开更多
Learning mathematics requires an effective and strategic teaching approach.This study aimed to assess the mathematics performance of the learners with the implementation of the numeracy enhancement strategy QD2R(Quest...Learning mathematics requires an effective and strategic teaching approach.This study aimed to assess the mathematics performance of the learners with the implementation of the numeracy enhancement strategy QD2R(Questions,Drills,Repetition,and Recitation)and to propose a strategy implementation plan to elevate their performances.This study employed the use of a quasi-experimental research design,purposive sampling with 70 Grade 10 students of Lian National High School who were distributed equally to control and treatment groups.The pre-test and post-test results were statistically analyzed using independent and paired sample t-tests,and a survey questionnaire was examined by getting the mean and standard deviation.The results indicated that better performance was achieved by the students from the treatment group compared to the students from the control group,as revealed by the Mean Percentage Score(MPS)results,mean scores,and P values of their pre-test and post-test scores.The learners’perception of the implementation of this strategy was to a great extent,wherein it was perceived to be more helpful in concepts related to understanding the lesson compared to concepts related to developing their attitude and skills.Moreover,the proposed implementation plan of numeracy enhancement strategy QD2R had three expected outcomes:elevated understanding and performance in mathematics lessons;modified strategy to focus on the development of attitude and skills towards mathematics;and refined and well-implemented QD2R strategy in teaching mathematics.Relative to these expected outcomes,appropriate measures,timeframe,and resources of each were comprehensively formulated.展开更多
“阅读圈”是一种学生自主阅读、讨论与分享的活动。小学生的英语语言能力、合作能力、组织能力都较弱,教师应根据学情,参照学业质量要求,对“阅读圈”中的角色任务进行指导。文章以“沪教版”牛津英语3AM4U3 The life cycle of the se...“阅读圈”是一种学生自主阅读、讨论与分享的活动。小学生的英语语言能力、合作能力、组织能力都较弱,教师应根据学情,参照学业质量要求,对“阅读圈”中的角色任务进行指导。文章以“沪教版”牛津英语3AM4U3 The life cycle of the seeds教学为例,通过对“提问专家”(Question asker)角色任务的分析,归纳角色孵化的实施路径,并提出优化建议。展开更多
本文的标题中的Questioned系动词question的被动形式。若标题不作省略,其完整表达应当是:Advice to Drink Liquids During a Cold Is Questioned。汉语的相应表达应该是:患感冒期间应该多喝水的建议受到质疑。是啊,感冒了?多喝水!这确...本文的标题中的Questioned系动词question的被动形式。若标题不作省略,其完整表达应当是:Advice to Drink Liquids During a Cold Is Questioned。汉语的相应表达应该是:患感冒期间应该多喝水的建议受到质疑。是啊,感冒了?多喝水!这确实是一个universally recommending advice,读者朋友,读了此文,你可要多个心眼哟!展开更多
Over the last couple of decades,community question-answering sites(CQAs)have been a topic of much academic interest.Scholars have often leveraged traditional machine learning(ML)and deep learning(DL)to explore the eve...Over the last couple of decades,community question-answering sites(CQAs)have been a topic of much academic interest.Scholars have often leveraged traditional machine learning(ML)and deep learning(DL)to explore the ever-growing volume of content that CQAs engender.To clarify the current state of the CQA literature that has used ML and DL,this paper reports a systematic literature review.The goal is to summarise and synthesise the major themes of CQA research related to(i)questions,(ii)answers and(iii)users.The final review included 133 articles.Dominant research themes include question quality,answer quality,and expert identification.In terms of dataset,some of the most widely studied platforms include Yahoo!Answers,Stack Exchange and Stack Overflow.The scope of most articles was confined to just one platform with few cross-platform investigations.Articles with ML outnumber those with DL.Nonetheless,the use of DL in CQA research is on an upward trajectory.A number of research directions are proposed.展开更多
Recently,pre-trained language representation models such as bidirec-tional encoder representations from transformers(BERT)have been performing well in commonsense question answering(CSQA).However,there is a problem th...Recently,pre-trained language representation models such as bidirec-tional encoder representations from transformers(BERT)have been performing well in commonsense question answering(CSQA).However,there is a problem that the models do not directly use explicit information of knowledge sources existing outside.To augment this,additional methods such as knowledge-aware graph network(KagNet)and multi-hop graph relation network(MHGRN)have been proposed.In this study,we propose to use the latest pre-trained language model a lite bidirectional encoder representations from transformers(ALBERT)with knowledge graph information extraction technique.We also propose to applying the novel method,schema graph expansion to recent language models.Then,we analyze the effect of applying knowledge graph-based knowledge extraction techniques to recent pre-trained language models and confirm that schema graph expansion is effective in some extent.Furthermore,we show that our proposed model can achieve better performance than existing KagNet and MHGRN models in CommonsenseQA dataset.展开更多
Analyzing Research and Development(R&D)trends is important because it can influence future decisions regarding R&D direction.In typical trend analysis,topic or technology taxonomies are employed to compute the...Analyzing Research and Development(R&D)trends is important because it can influence future decisions regarding R&D direction.In typical trend analysis,topic or technology taxonomies are employed to compute the popularities of the topics or codes over time.Although it is simple and effective,the taxonomies are difficult to manage because new technologies are introduced rapidly.Therefore,recent studies exploit deep learning to extract pre-defined targets such as problems and solutions.Based on the recent advances in question answering(QA)using deep learning,we adopt a multi-turn QA model to extract problems and solutions from Korean R&D reports.With the previous research,we use the reports directly and analyze the difficulties in handling them using QA style on Information Extraction(IE)for sentence-level benchmark dataset.After investigating the characteristics of Korean R&D,we propose a model to deal with multiple and repeated appearances of targets in the reports.Accordingly,we propose a model that includes an algorithm with two novel modules and a prompt.A newly proposed methodology focuses on reformulating a question without a static template or pre-defined knowledge.We show the effectiveness of the proposed model using a Korean R&D report dataset that we constructed and presented an in-depth analysis of the benefits of the multi-turn QA model.展开更多
ExpertRecommendation(ER)aims to identify domain experts with high expertise and willingness to provide answers to questions in Community Question Answering(CQA)web services.How to model questions and users in the hete...ExpertRecommendation(ER)aims to identify domain experts with high expertise and willingness to provide answers to questions in Community Question Answering(CQA)web services.How to model questions and users in the heterogeneous content network is critical to this task.Most traditional methods focus on modeling questions and users based on the textual content left in the community while ignoring the structural properties of heterogeneous CQA networks and always suffering from textual data sparsity issues.Recent approaches take advantage of structural proximities between nodes and attempt to fuse the textual content of nodes for modeling.However,they often fail to distinguish the nodes’personalized preferences and only consider the textual content of a part of the nodes in network embedding learning,while ignoring the semantic relevance of nodes.In this paper,we propose a novel framework that jointly considers the structural proximity relations and textual semantic relevance to model users and questions more comprehensively.Specifically,we learn topology-based embeddings through a hierarchical attentive network learning strategy,in which the proximity information and the personalized preference of nodes are encoded and preserved.Meanwhile,we utilize the node’s textual content and the text correlation between adjacent nodes to build the content-based embedding through a meta-context-aware skip-gram model.In addition,the user’s relative answer quality is incorporated to promote the ranking performance.Experimental results show that our proposed framework consistently and significantly outperforms the state-of-the-art baselines on three real-world datasets by taking the deep semantic understanding and structural feature learning together.The performance of the proposed work is analyzed in terms of MRR,P@K,and MAP and is proven to be more advanced than the existing methodologies.展开更多
Visual question answering(VQA)has attracted more and more attention in computer vision and natural language processing.Scholars are committed to studying how to better integrate image features and text features to ach...Visual question answering(VQA)has attracted more and more attention in computer vision and natural language processing.Scholars are committed to studying how to better integrate image features and text features to achieve better results in VQA tasks.Analysis of all features may cause information redundancy and heavy computational burden.Attention mechanism is a wise way to solve this problem.However,using single attention mechanism may cause incomplete concern of features.This paper improves the attention mechanism method and proposes a hybrid attention mechanism that combines the spatial attention mechanism method and the channel attention mechanism method.In the case that the attention mechanism will cause the loss of the original features,a small portion of image features were added as compensation.For the attention mechanism of text features,a selfattention mechanism was introduced,and the internal structural features of sentences were strengthened to improve the overall model.The results show that attention mechanism and feature compensation add 6.1%accuracy to multimodal low-rank bilinear pooling network.展开更多
The original intention of visual question answering(VQA)models is to infer the answer based on the relevant information of the question text in the visual image,but many VQA models often yield answers that are biased ...The original intention of visual question answering(VQA)models is to infer the answer based on the relevant information of the question text in the visual image,but many VQA models often yield answers that are biased by some prior knowledge,especially the language priors.This paper proposes a mitigation model called language priors mitigation-VQA(LPM-VQA)for the language priors problem in VQA model,which divides language priors into positive and negative language priors.Different network branches are used to capture and process the different priors to achieve the purpose of mitigating language priors.A dynamically-changing language prior feedback objective function is designed with the intermediate results of some modules in the VQA model.The weight of the loss value for each answer is dynamically set according to the strength of its language priors to balance its proportion in the total VQA loss to further mitigate the language priors.This model does not depend on the baseline VQA architectures and can be configured like a plug-in to improve the performance of the model over most existing VQA models.The experimental results show that the proposed model is general and effective,achieving state-of-the-art accuracy in the VQA-CP v2 dataset.展开更多
The described structural model tries to answer some open questions such as: Why do quarks not exist in the open state? Where are the antiparticles from the Big Bang?
The Taiwan Question China discussed in this paper belongs to the theoretical crisis discussion on international relations and does not regard the Cross-Strait relations as relations between different countries.The out...The Taiwan Question China discussed in this paper belongs to the theoretical crisis discussion on international relations and does not regard the Cross-Strait relations as relations between different countries.The outcome of the 2024 Taiwan Election has a great impact on the Taiwan question,the latest poll shows that the possibility of the Democratic Progressive Party(DPP)candidate to come to power is still very high,because its political evolution trend of Taiwan independence still exists.展开更多
When we think about our vision for education in 2050,several questions come to the mind:what practices should we keep?Which ones should we abandon?And which aspects require creative thinking for a redesign?UNESCO prov...When we think about our vision for education in 2050,several questions come to the mind:what practices should we keep?Which ones should we abandon?And which aspects require creative thinking for a redesign?UNESCO provided some answers to these crucial questions in a report published in November 2021 titled“Reimagining our futures together:a new social contract for education.”Against this backdrop,it called for a radical transformation of education aimed at addressing the injustices of the past and strengthening our collective resolve to work towards a more sustainable and equitable future.展开更多
The popularity of flexible working hours around the world has slowed down the historical trend of reducing working hours.It even shows signs of regression.Whether and how to guide the cur-rent society with flexible wo...The popularity of flexible working hours around the world has slowed down the historical trend of reducing working hours.It even shows signs of regression.Whether and how to guide the cur-rent society with flexible working hours to return to the historical track of reducing working hours,improve the quality of working hours,and promote a smooth transition from the era of traditional standard work-ing hours to the era of flexible working hours has become a question related to the legal regulation of working hours in the new era.In this regard,although Western countries have proposed new regulatory concepts and carried out legislative practices with distinctive charac-teristics,the limitations of legal regulation capabilities have prevented them from proposing a package of institutional solutions.The advan-tage of China in the ability of legal regulation of working hours has been gradually formed in the legislation on working hours unnder the leadership of the CPC in the past century.It enables China to break through the limitations of the West and propose a Chinese approach to answer the question of the legal regulation of working hours in the new era from three aspects:limiting the extension of working hours,improving the quality of flexible working hours,and optimizing the funnctions of the multi-funnctional regulatory system for working hours.展开更多
文摘Statistics released by China Customs in February,2007 showed an uncommon rapid growth in Shenzhen’s 2006 textile export.In 2006,the total value of textile
文摘China's central bank in October announced plans to expand a pilot program on credit assets to nine municipalities and provinces, allowing banks to pledge assets to borrow from the central bank. In August, China's top legislature adopted an amendment to the law on commercial banks, removing the 7S-percent loan- to-deposit ratio stipulation. Both measures have been interpreted by some financial institutions as a stimulus of 7 trillion yuan ($1.11 trillion) and a "Chinese- style quantitative easing (QE)" policy. In a recent article in the National Business Daily, chief bond analyst of Minsheng Securities Co. Ltd., believes that such judgment lacks logic. Edited excerpts of the article follow.
基金Supported by Sichuan Science and Technology Program(2021YFQ0003,2023YFSY0026,2023YFH0004).
文摘In the field of natural language processing(NLP),there have been various pre-training language models in recent years,with question answering systems gaining significant attention.However,as algorithms,data,and computing power advance,the issue of increasingly larger models and a growing number of parameters has surfaced.Consequently,model training has become more costly and less efficient.To enhance the efficiency and accuracy of the training process while reducing themodel volume,this paper proposes a first-order pruningmodel PAL-BERT based on the ALBERT model according to the characteristics of question-answering(QA)system and language model.Firstly,a first-order network pruning method based on the ALBERT model is designed,and the PAL-BERT model is formed.Then,the parameter optimization strategy of the PAL-BERT model is formulated,and the Mish function was used as an activation function instead of ReLU to improve the performance.Finally,after comparison experiments with traditional deep learning models TextCNN and BiLSTM,it is confirmed that PALBERT is a pruning model compression method that can significantly reduce training time and optimize training efficiency.Compared with traditional models,PAL-BERT significantly improves the NLP task’s performance.
基金the Specific Research Project of Guangxi for Research Bases and Talents,No.GuiKe AD22035057the National Natural Science Foundation of China,No.82060510 and No.82260569.
文摘Approximately 50%-70%of patients with hepatocellular carcinoma experience recurrence within five years after curative hepatic resection or ablation.As a result,many patients receive adjuvant therapy after curative resection or ablation in order to prolong recurrence-free survival.The therapy recommended by national guidelines can differ,and guidelines do not specify when to initiate adjuvant therapy or how long to continue it.These and other unanswered questions around adjuvant therapies make it difficult to optimize them and determine which may be more appropriate for a given type of patient.These questions need to be addressed by clinicians and researchers.
文摘The weapon and equipment operational requirement analysis(WEORA) is a necessary condition to win a future war,among which the acquisition of knowledge about weapons and equipment is a great challenge. The main challenge is that the existing weapons and equipment data fails to carry out structured knowledge representation, and knowledge navigation based on natural language cannot efficiently support the WEORA. To solve above problem, this research proposes a method based on question answering(QA) of weapons and equipment knowledge graph(WEKG) to construct and navigate the knowledge related to weapons and equipment in the WEORA. This method firstly constructs the WEKG, and builds a neutral network-based QA system over the WEKG by means of semantic parsing for knowledge navigation. Finally, the method is evaluated and a chatbot on the QA system is developed for the WEORA. Our proposed method has good performance in the accuracy and efficiency of searching target knowledge, and can well assist the WEORA.
文摘Visual Question Answering(VQA)has sparked widespread interest as a crucial task in integrating vision and language.VQA primarily uses attention mechanisms to effectively answer questions to associate relevant visual regions with input questions.The detection-based features extracted by the object detection network aim to acquire the visual attention distribution on a predetermined detection frame and provide object-level insights to answer questions about foreground objects more effectively.However,it cannot answer the question about the background forms without detection boxes due to the lack of fine-grained details,which is the advantage of grid-based features.In this paper,we propose a Dual-Level Feature Embedding(DLFE)network,which effectively integrates grid-based and detection-based image features in a unified architecture to realize the complementary advantages of both features.Specifically,in DLFE,In DLFE,firstly,a novel Dual-Level Self-Attention(DLSA)modular is proposed to mine the intrinsic properties of the two features,where Positional Relation Attention(PRA)is designed to model the position information.Then,we propose a Feature Fusion Attention(FFA)to address the semantic noise caused by the fusion of two features and construct an alignment graph to enhance and align the grid and detection features.Finally,we use co-attention to learn the interactive features of the image and question and answer questions more accurately.Our method has significantly improved compared to the baseline,increasing accuracy from 66.01%to 70.63%on the test-std dataset of VQA 1.0 and from 66.24%to 70.91%for the test-std dataset of VQA 2.0.
文摘Learning mathematics requires an effective and strategic teaching approach.This study aimed to assess the mathematics performance of the learners with the implementation of the numeracy enhancement strategy QD2R(Questions,Drills,Repetition,and Recitation)and to propose a strategy implementation plan to elevate their performances.This study employed the use of a quasi-experimental research design,purposive sampling with 70 Grade 10 students of Lian National High School who were distributed equally to control and treatment groups.The pre-test and post-test results were statistically analyzed using independent and paired sample t-tests,and a survey questionnaire was examined by getting the mean and standard deviation.The results indicated that better performance was achieved by the students from the treatment group compared to the students from the control group,as revealed by the Mean Percentage Score(MPS)results,mean scores,and P values of their pre-test and post-test scores.The learners’perception of the implementation of this strategy was to a great extent,wherein it was perceived to be more helpful in concepts related to understanding the lesson compared to concepts related to developing their attitude and skills.Moreover,the proposed implementation plan of numeracy enhancement strategy QD2R had three expected outcomes:elevated understanding and performance in mathematics lessons;modified strategy to focus on the development of attitude and skills towards mathematics;and refined and well-implemented QD2R strategy in teaching mathematics.Relative to these expected outcomes,appropriate measures,timeframe,and resources of each were comprehensively formulated.
文摘“阅读圈”是一种学生自主阅读、讨论与分享的活动。小学生的英语语言能力、合作能力、组织能力都较弱,教师应根据学情,参照学业质量要求,对“阅读圈”中的角色任务进行指导。文章以“沪教版”牛津英语3AM4U3 The life cycle of the seeds教学为例,通过对“提问专家”(Question asker)角色任务的分析,归纳角色孵化的实施路径,并提出优化建议。
文摘本文的标题中的Questioned系动词question的被动形式。若标题不作省略,其完整表达应当是:Advice to Drink Liquids During a Cold Is Questioned。汉语的相应表达应该是:患感冒期间应该多喝水的建议受到质疑。是啊,感冒了?多喝水!这确实是一个universally recommending advice,读者朋友,读了此文,你可要多个心眼哟!
文摘Over the last couple of decades,community question-answering sites(CQAs)have been a topic of much academic interest.Scholars have often leveraged traditional machine learning(ML)and deep learning(DL)to explore the ever-growing volume of content that CQAs engender.To clarify the current state of the CQA literature that has used ML and DL,this paper reports a systematic literature review.The goal is to summarise and synthesise the major themes of CQA research related to(i)questions,(ii)answers and(iii)users.The final review included 133 articles.Dominant research themes include question quality,answer quality,and expert identification.In terms of dataset,some of the most widely studied platforms include Yahoo!Answers,Stack Exchange and Stack Overflow.The scope of most articles was confined to just one platform with few cross-platform investigations.Articles with ML outnumber those with DL.Nonetheless,the use of DL in CQA research is on an upward trajectory.A number of research directions are proposed.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea Government(MSIT)(No.2020R1G1A1100493).
文摘Recently,pre-trained language representation models such as bidirec-tional encoder representations from transformers(BERT)have been performing well in commonsense question answering(CSQA).However,there is a problem that the models do not directly use explicit information of knowledge sources existing outside.To augment this,additional methods such as knowledge-aware graph network(KagNet)and multi-hop graph relation network(MHGRN)have been proposed.In this study,we propose to use the latest pre-trained language model a lite bidirectional encoder representations from transformers(ALBERT)with knowledge graph information extraction technique.We also propose to applying the novel method,schema graph expansion to recent language models.Then,we analyze the effect of applying knowledge graph-based knowledge extraction techniques to recent pre-trained language models and confirm that schema graph expansion is effective in some extent.Furthermore,we show that our proposed model can achieve better performance than existing KagNet and MHGRN models in CommonsenseQA dataset.
基金the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(NRF-2019R1G1A1003312)the Ministry of Education(NRF-2021R1I1A3052815).
文摘Analyzing Research and Development(R&D)trends is important because it can influence future decisions regarding R&D direction.In typical trend analysis,topic or technology taxonomies are employed to compute the popularities of the topics or codes over time.Although it is simple and effective,the taxonomies are difficult to manage because new technologies are introduced rapidly.Therefore,recent studies exploit deep learning to extract pre-defined targets such as problems and solutions.Based on the recent advances in question answering(QA)using deep learning,we adopt a multi-turn QA model to extract problems and solutions from Korean R&D reports.With the previous research,we use the reports directly and analyze the difficulties in handling them using QA style on Information Extraction(IE)for sentence-level benchmark dataset.After investigating the characteristics of Korean R&D,we propose a model to deal with multiple and repeated appearances of targets in the reports.Accordingly,we propose a model that includes an algorithm with two novel modules and a prompt.A newly proposed methodology focuses on reformulating a question without a static template or pre-defined knowledge.We show the effectiveness of the proposed model using a Korean R&D report dataset that we constructed and presented an in-depth analysis of the benefits of the multi-turn QA model.
文摘ExpertRecommendation(ER)aims to identify domain experts with high expertise and willingness to provide answers to questions in Community Question Answering(CQA)web services.How to model questions and users in the heterogeneous content network is critical to this task.Most traditional methods focus on modeling questions and users based on the textual content left in the community while ignoring the structural properties of heterogeneous CQA networks and always suffering from textual data sparsity issues.Recent approaches take advantage of structural proximities between nodes and attempt to fuse the textual content of nodes for modeling.However,they often fail to distinguish the nodes’personalized preferences and only consider the textual content of a part of the nodes in network embedding learning,while ignoring the semantic relevance of nodes.In this paper,we propose a novel framework that jointly considers the structural proximity relations and textual semantic relevance to model users and questions more comprehensively.Specifically,we learn topology-based embeddings through a hierarchical attentive network learning strategy,in which the proximity information and the personalized preference of nodes are encoded and preserved.Meanwhile,we utilize the node’s textual content and the text correlation between adjacent nodes to build the content-based embedding through a meta-context-aware skip-gram model.In addition,the user’s relative answer quality is incorporated to promote the ranking performance.Experimental results show that our proposed framework consistently and significantly outperforms the state-of-the-art baselines on three real-world datasets by taking the deep semantic understanding and structural feature learning together.The performance of the proposed work is analyzed in terms of MRR,P@K,and MAP and is proven to be more advanced than the existing methodologies.
基金This work was supported by the Sichuan Science and Technology Program(2021YFQ0003).
文摘Visual question answering(VQA)has attracted more and more attention in computer vision and natural language processing.Scholars are committed to studying how to better integrate image features and text features to achieve better results in VQA tasks.Analysis of all features may cause information redundancy and heavy computational burden.Attention mechanism is a wise way to solve this problem.However,using single attention mechanism may cause incomplete concern of features.This paper improves the attention mechanism method and proposes a hybrid attention mechanism that combines the spatial attention mechanism method and the channel attention mechanism method.In the case that the attention mechanism will cause the loss of the original features,a small portion of image features were added as compensation.For the attention mechanism of text features,a selfattention mechanism was introduced,and the internal structural features of sentences were strengthened to improve the overall model.The results show that attention mechanism and feature compensation add 6.1%accuracy to multimodal low-rank bilinear pooling network.
文摘The original intention of visual question answering(VQA)models is to infer the answer based on the relevant information of the question text in the visual image,but many VQA models often yield answers that are biased by some prior knowledge,especially the language priors.This paper proposes a mitigation model called language priors mitigation-VQA(LPM-VQA)for the language priors problem in VQA model,which divides language priors into positive and negative language priors.Different network branches are used to capture and process the different priors to achieve the purpose of mitigating language priors.A dynamically-changing language prior feedback objective function is designed with the intermediate results of some modules in the VQA model.The weight of the loss value for each answer is dynamically set according to the strength of its language priors to balance its proportion in the total VQA loss to further mitigate the language priors.This model does not depend on the baseline VQA architectures and can be configured like a plug-in to improve the performance of the model over most existing VQA models.The experimental results show that the proposed model is general and effective,achieving state-of-the-art accuracy in the VQA-CP v2 dataset.
文摘The described structural model tries to answer some open questions such as: Why do quarks not exist in the open state? Where are the antiparticles from the Big Bang?
文摘The Taiwan Question China discussed in this paper belongs to the theoretical crisis discussion on international relations and does not regard the Cross-Strait relations as relations between different countries.The outcome of the 2024 Taiwan Election has a great impact on the Taiwan question,the latest poll shows that the possibility of the Democratic Progressive Party(DPP)candidate to come to power is still very high,because its political evolution trend of Taiwan independence still exists.
文摘When we think about our vision for education in 2050,several questions come to the mind:what practices should we keep?Which ones should we abandon?And which aspects require creative thinking for a redesign?UNESCO provided some answers to these crucial questions in a report published in November 2021 titled“Reimagining our futures together:a new social contract for education.”Against this backdrop,it called for a radical transformation of education aimed at addressing the injustices of the past and strengthening our collective resolve to work towards a more sustainable and equitable future.
基金funded by the National Social Science Fund of China (Western Region Program)“Research on Improving the Quality of Legislation in China on Rest and Vacation from a Global Perspective”(Project Approval Number:19XFX014)。
文摘The popularity of flexible working hours around the world has slowed down the historical trend of reducing working hours.It even shows signs of regression.Whether and how to guide the cur-rent society with flexible working hours to return to the historical track of reducing working hours,improve the quality of working hours,and promote a smooth transition from the era of traditional standard work-ing hours to the era of flexible working hours has become a question related to the legal regulation of working hours in the new era.In this regard,although Western countries have proposed new regulatory concepts and carried out legislative practices with distinctive charac-teristics,the limitations of legal regulation capabilities have prevented them from proposing a package of institutional solutions.The advan-tage of China in the ability of legal regulation of working hours has been gradually formed in the legislation on working hours unnder the leadership of the CPC in the past century.It enables China to break through the limitations of the West and propose a Chinese approach to answer the question of the legal regulation of working hours in the new era from three aspects:limiting the extension of working hours,improving the quality of flexible working hours,and optimizing the funnctions of the multi-funnctional regulatory system for working hours.