Attention-based BiGRU-CNN for Chinese question classification

Liu, Jin; Yang, Yihe; Lv, Shiqi; Wang, Jin; Chen, Hui

doi:10.1007/s12652-019-01344-9

Cited by 98 publications

(44 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to measure the performance of our model, we compared it to other representative methods. As shown in Table 5 [4]) or attention mechanism (such as BiDAF [10]). AG-MTA combines the context information and extracts key semantic information by using MTA module, position encoding, and multi-head attention mechanism.…”

Section: Ablation Studies and Comparisons With Prior Methodsmentioning

confidence: 99%

“…In experiments, we used the SQuAD [4] data set proposed by Rajpurkar et al It contains a total of 107,785 questions, as well as 536 pieces of material that contain the target We aggregate each multi-layer attention transformer unit between aggregation nodes and transmit the aggregated information to the backbone network to further enhance the utilization of information. In addition, since each layer transmits information in parallel, the computational efficiency of the model is improved.…”

Section: Experiments a Datasetmentioning

confidence: 99%

“…Table 1 shows an example of the SQuAD data set. SQuAD [4] has extracted more than 100,000 questionanswer pairs from hundreds of articles on Wikipedia through crowdsourcing. Compared to other datasets like MCTest [27], Algebra [28], Science [29] and WiKiQA [30], the reason we chose the SQuAD dataset is that the number of questions in SQuAD is far greater than them.…”

Section: Experiments a Datasetmentioning

confidence: 99%

“…Then, the QANet [2] improves the speed and accuracy of answer generation by combining Convolutional Neural Network (CNN) and LSTM, and achieved reliable results on the SQuAD [3] dataset. Recent method [4] combines the CNN network and attention mechanism for Chinese question classification, which boosts the effect of the answer generation.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Multi-Layer Transformer Aggregation Encoder for Answer Generation

2020

Self Cite

View full text Add to dashboard Cite

Answer generation is one of the most important tasks in natural language processing, and deep learning-based methods have shown their strength over traditional machine learning based methods. However, most previous deep learning-based answer generation models were built on traditional recurrent neural networks or convolutional neural networks. The former model cannot well exploit contextual correlation preserved in paragraphs due to their inherent computation complexity. For the latter, since the size of the convolutional kernel is fixed, the model cannot extract complete semantic information features. In order to alleviate this problem, based on multi-layer Transformer aggregation coder, we propose an end-toend answer generation model (AG-MTA). AG-MTA consists of a multi-layer attention Transformer unit and a multi-layer attention Transformer aggregation encoder (MTA). It can focus on information representation at different positions and aggregate nodes at same layer to combine the context information. Thereby, it fuses semantic information from base layer to top layer, enhancing the information representation of the encoder. Furthermore, based on trigonometric function, a novel position encoding method is also proposed. Experiments are conducted on public datasets SQuAD. AG-MTA reaches the state-of-the-art performance, EM score achieves 71.1 and F1 score achieves 80.3. INDEX TERMS Question answering system, natural language processing, self-attention mechanism, transformer coding structure.

show abstract

Section: Ablation Studies and Comparisons With Prior Methodsmentioning

confidence: 99%

Section: Experiments a Datasetmentioning

confidence: 99%

Section: Experiments a Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Layer Transformer Aggregation Encoder for Answer Generation

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…It comprehensively includes a variety of important techniques, such as image processing, pattern recognition, artificial intelligence and machine learning. It has broad application prospects in such areas such as road traffic accident prevention [1], warnings of dangerous goods in factories, military restricted area monitoring and advanced human-computer interaction [2,3]. Since the application scenarios of multi-target detection in the real world are usually complex and variable, balancing the relationship between accuracy and computing costs is a difficult task.The object detection process is traditionally established by manually extracting feature models, where the common features are represented by HOG (histogram of oriented…”

mentioning

confidence: 99%

An improved object detection algorithm based on multi-scaled and deformable convolutional neural networks

Cao

Chen

Gao

2020

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

IntroductionThe main purpose of object detection is to identify and locate one or more effective targets from still image or video data. It comprehensively includes a variety of important techniques, such as image processing, pattern recognition, artificial intelligence and machine learning. It has broad application prospects in such areas such as road traffic accident prevention [1], warnings of dangerous goods in factories, military restricted area monitoring and advanced human-computer interaction [2,3]. Since the application scenarios of multi-target detection in the real world are usually complex and variable, balancing the relationship between accuracy and computing costs is a difficult task.The object detection process is traditionally established by manually extracting feature models, where the common features are represented by HOG (histogram of oriented AbstractObject detection methods aim to identify all target objects in the target image and determine the categories and position information in order to achieve machine vision understanding. Numerous approaches have been proposed to solve this problem, mainly inspired by methods of computer vision and deep learning. However, existing approaches always perform poorly for the detection of small, dense objects, and even fail to detect objects with random geometric transformations. In this study, we compare and analyse mainstream object detection algorithms and propose a multi-scaled deformable convolutional object detection network to deal with the challenges faced by current methods. Our analysis demonstrates a strong performance on par, or even better, than state of the art methods. We use deep convolutional networks to obtain multi-scaled features, and add deformable convolutional structures to overcome geometric transformations. We then fuse the multi-scaled features by up sampling, in order to implement the final object recognition and region regress. Experiments prove that our suggested framework improves the accuracy of detecting small target objects with geometric deformation, showing significant improvements in the trade-off between accuracy and speed.

show abstract

Senti‐eSystem: A sentiment‐based eSystem‐using hybridized fuzzy and deep neural network for measuring customer satisfaction

et al. 2020

View full text Add to dashboard Cite

Summary In the competing era of online industries, understanding customer feedback and satisfaction is one of the important concern for any business organization. The well‐known social media platforms like Twitter are a place where customers share their feedbacks. Analyzing customer feedback is beneficial, as it provides an advantage way of unveiling customer interests. The proposed system, namely Senti‐eSystem, aims at the development of sentiment‐based eSystem using hybridized Fuzzy and Deep Neural Network for Measuring Customer Satisfaction to assist business organizations for improving the quality of their services and products. The proposed approach initially deploys a Bidirectional Long Short Term Memory with attention mechanism to predict the sentiment polarity that is positive and negative, followed by Fuzzy logic approach to determine the customer satisfaction level, which further strengthens the capabilities of the proposed approach. The system achieves an accuracy of 92.86%, outperforming the previous state‐of‐art lexicon‐based approaches. Moreover, the effectiveness of the proposed system is also validated by applying the statistical test.

show abstract

Attention-based BiGRU-CNN for Chinese question classification

Cited by 98 publications

References 27 publications

Multi-Layer Transformer Aggregation Encoder for Answer Generation

Multi-Layer Transformer Aggregation Encoder for Answer Generation

An improved object detection algorithm based on multi-scaled and deformable convolutional neural networks

Senti‐eSystem: A sentiment‐based eSystem‐using hybridized fuzzy and deep neural network for measuring customer satisfaction

Contact Info

Product

Resources

About