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
Recent advancements in natural language processing have given rise to numerous pre-training language models in question-answering systems.However,with the constant evolution of algorithms,data,and computing power,the ...Recent advancements in natural language processing have given rise to numerous pre-training language models in question-answering systems.However,with the constant evolution of algorithms,data,and computing power,the increasing size and complexity of these models have led to increased training costs and reduced efficiency.This study aims to minimize the inference time of such models while maintaining computational performance.It also proposes a novel Distillation model for PAL-BERT(DPAL-BERT),specifically,employs knowledge distillation,using the PAL-BERT model as the teacher model to train two student models:DPAL-BERT-Bi and DPAL-BERTC.This research enhances the dataset through techniques such as masking,replacement,and n-gram sampling to optimize knowledge transfer.The experimental results showed that the distilled models greatly outperform models trained from scratch.In addition,although the distilled models exhibit a slight decrease in performance compared to PAL-BERT,they significantly reduce inference time to just 0.25%of the original.This demonstrates the effectiveness of the proposed approach in balancing model performance and efficiency.展开更多
The conversation machine comprehension(MC)task aims to answer questions in the multi-turn conversation for a single passage.However,recent approaches don’t exploit information from historical conversations effectivel...The conversation machine comprehension(MC)task aims to answer questions in the multi-turn conversation for a single passage.However,recent approaches don’t exploit information from historical conversations effectively,which results in some references and ellipsis in the current question cannot be recognized.In addition,these methods do not consider the rich semantic relationships between words when reasoning about the passage text.In this paper,we propose a novel model GraphFlow+,which constructs a context graph for each conversation turn and uses a unique recurrent graph neural network(GNN)to model the temporal dependencies between the context graphs of each turn.Specifically,we exploit three different ways to construct text graphs,including the dynamic graph,static graph,and hybrid graph that combines the two.Our experiments on CoQA,QuAC and DoQA show that the GraphFlow+model can outperform the state-of-the-art approaches.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
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 information integration method of semantic web based on agent ontology(SWAO method) was put forward aiming at the problems in current network environment,which integrates,analyzes and processes enormous web inform...The information integration method of semantic web based on agent ontology(SWAO method) was put forward aiming at the problems in current network environment,which integrates,analyzes and processes enormous web information and extracts answers on the basis of semantics. With SWAO method as the clue,the following technologies were studied:the method of concept extraction based on semantic term mining,agent ontology construction method on account of multi-points and the answer extraction in view of semantic inference. Meanwhile,the structural model of the question answering system applying ontology was presented,which adopts OWL language to describe domain knowledge from where QA system infers and extracts answers by Jena inference engine. In the system testing,the precision rate reaches 86%,and the recalling rate is 93%. The experimental results prove that it is feasible to use the method to develop a question answering system,which is valuable for further study in more depth.展开更多
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.
基金supported by Sichuan Science and Technology Program(2023YFSY0026,2023YFH0004).
文摘Recent advancements in natural language processing have given rise to numerous pre-training language models in question-answering systems.However,with the constant evolution of algorithms,data,and computing power,the increasing size and complexity of these models have led to increased training costs and reduced efficiency.This study aims to minimize the inference time of such models while maintaining computational performance.It also proposes a novel Distillation model for PAL-BERT(DPAL-BERT),specifically,employs knowledge distillation,using the PAL-BERT model as the teacher model to train two student models:DPAL-BERT-Bi and DPAL-BERTC.This research enhances the dataset through techniques such as masking,replacement,and n-gram sampling to optimize knowledge transfer.The experimental results showed that the distilled models greatly outperform models trained from scratch.In addition,although the distilled models exhibit a slight decrease in performance compared to PAL-BERT,they significantly reduce inference time to just 0.25%of the original.This demonstrates the effectiveness of the proposed approach in balancing model performance and efficiency.
文摘The conversation machine comprehension(MC)task aims to answer questions in the multi-turn conversation for a single passage.However,recent approaches don’t exploit information from historical conversations effectively,which results in some references and ellipsis in the current question cannot be recognized.In addition,these methods do not consider the rich semantic relationships between words when reasoning about the passage text.In this paper,we propose a novel model GraphFlow+,which constructs a context graph for each conversation turn and uses a unique recurrent graph neural network(GNN)to model the temporal dependencies between the context graphs of each turn.Specifically,we exploit three different ways to construct text graphs,including the dynamic graph,static graph,and hybrid graph that combines the two.Our experiments on CoQA,QuAC and DoQA show that the GraphFlow+model can outperform the state-of-the-art approaches.
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.
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.
基金Projects(60773462, 60672171) supported by the National Natural Science Foundation of ChinaProjects(2009AA12143, 2009AA012136) supported by the National High-Tech Research and Development Program of ChinaProject(20080430250) supported by the Foundation of Post-Doctor in China
文摘The information integration method of semantic web based on agent ontology(SWAO method) was put forward aiming at the problems in current network environment,which integrates,analyzes and processes enormous web information and extracts answers on the basis of semantics. With SWAO method as the clue,the following technologies were studied:the method of concept extraction based on semantic term mining,agent ontology construction method on account of multi-points and the answer extraction in view of semantic inference. Meanwhile,the structural model of the question answering system applying ontology was presented,which adopts OWL language to describe domain knowledge from where QA system infers and extracts answers by Jena inference engine. In the system testing,the precision rate reaches 86%,and the recalling rate is 93%. The experimental results prove that it is feasible to use the method to develop a question answering system,which is valuable for further study in more depth.
