Filters








54,062 Hits in 3.6 sec

Learning to Generate Questions with Adaptive Copying Neural Networks [article]

Xinyuan Lu, Yuhong Guo
2019 arXiv   pre-print
In this paper we propose a novel adaptive copying recurrent neural network model to tackle the problem of question generation from sentences and paragraphs.  ...  The proposed model adds a copying mechanism component onto a bidirectional LSTM architecture to generate more suitable questions adaptively from the input data.  ...  Conclusion and Future Work In this paper, we proposed an adaptive copying neural network (ACNN) model for question generation.  ... 
arXiv:1909.08187v1 fatcat:xwitecz25rhurpwivmdti3w34a

Multi-Scale Deformable CNN for Answer Selection

Donglei Liu, Zhendong Niu, Chunxia Zhang, Jiadi Zhang
2019 IEEE Access  
INDEX TERMS Answer selection, deformable convolution neural network, sentence modeling, question answering. 164986 This work is licensed under a Creative Commons Attribution 4.0 License.  ...  Nowadays, many question answering systems adopt deep neural networks such as convolutional neural network (CNN) to generate the text features automatically, and obtained better performance than traditional  ...  ACKNOWLEDGMENT The authors would like to thank the editor and all reviewers for their suggestions that have helped to improve the work.  ... 
doi:10.1109/access.2019.2953219 fatcat:z7k3w7wp6rbgbgwwifay4xeolm

A Novel Bidirectional LSTM and Attention Mechanism based Neural Network for Answer Selection in Community Question Answering

Zhang Bo, Wang Haowen, Jiang Longquan, Yuan Shuhan, Li Meizi
2019 Computers Materials & Continua  
The existing models, which employ encoder-decoder recurrent neural network (RNN), have been demonstrated to be effective.  ...  Deep learning models have been shown to have great advantages in answer selection tasks.  ...  a novel network for answer selection tasks in CQA.  ... 
doi:10.32604/cmc.2020.07269 fatcat:yk63h35krzf7hkcnmiklrxmjoe

RankQA: Neural Question Answering with Answer Re-Ranking [article]

Bernhard Kratzwald, Anna Eigenmann, Stefan Feuerriegel
2019 arXiv   pre-print
The conventional paradigm in neural question answering (QA) for narrative content is limited to a two-stage process: first, relevant text passages are retrieved and, subsequently, a neural network for  ...  In contrast, this work proposes RankQA: RankQA extends the conventional two-stage process in neural QA with a third stage that performs an additional answer re-ranking.  ...  Acknowledgments We thank the anonymous reviewers for their helpful comments. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPUs used for this research.  ... 
arXiv:1906.03008v2 fatcat:evb46nkwmzdw7hqjikl2mcvmdm

RankQA: Neural Question Answering with Answer Re-Ranking

Bernhard Kratzwald, Anna Eigenmann, Stefan Feuerriegel
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
The conventional paradigm in neural question answering (QA) for narrative content is limited to a two-stage process: first, relevant text passages are retrieved and, subsequently, a neural network for  ...  In contrast, this work proposes RankQA 1 : RankQA extends the conventional two-stage process in neural QA with a third stage that performs an additional answer reranking.  ...  Acknowledgments We thank the anonymous reviewers for their helpful comments. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPUs used for this research.  ... 
doi:10.18653/v1/p19-1611 dblp:conf/acl/KratzwaldEF19 fatcat:2zj2fx56wfcubaxbx5iqrwfkuq

History-Adaption Knowledge Incorporation Mechanism for Multi-Turn Dialogue System

Yajing Sun, Yue Hu, Luxi Xing, Jing Yu, Yuqiang Xie
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
So we design a history-adaption knowledge incorporation mechanism to build an effective multi-turn dialogue model.  ...  The network takes context C, knowledge sentences P and candidate answers A as inputs and selects appropriate answer.  ...  data and powerful models learned based on the neural networks.  ... 
doi:10.1609/aaai.v34i05.6425 fatcat:vfhq4lvm65gfhdsjlvkaq4mmuq

Survey of reasoning using Neural networks [article]

Amit Sahu
2017 arXiv   pre-print
Most prominent neural architectures for such tasks are Memory networks: inference components combined with long term memory and Neural Turing Machines: neural networks using external memory resources.  ...  Still, it poses many challenges like, how to train neural networks for discrete memory representation, how to describe long term dependencies in sequential data etc.  ...  For example network trained to copy sequences of length 20 was tested on sequences of length 100.  ... 
arXiv:1702.06186v2 fatcat:y6btabr3qrf3lnxbete44tfxym

Web Intelligent for Forecasting Exchange Rate Currency using Clever Extraction Agent Combine with Financial Data Mining

Khammapun Khantanapoka
2021 International Journal of Mathematics and Computers in Simulation  
Kohonen Neural Networks is the method to determine similarity of internet documents using pattern index of financial document.  ...  It is analyzed for exchange rate forecasting about USD/ Pounds.  ...  The properties of chromosome measured adapting to answer Ninth step is comparison for fitness function in each round. We compare each fitness function in the same round.  ... 
doi:10.46300/9102.2021.15.1 fatcat:om5gqykorjhefjgzxpwslwvtb4

ICRC-HIT: A Deep Learning based Comment Sequence Labeling System for Answer Selection Challenge

Xiaoqiang Zhou, Baotian Hu, Jiaxin Lin, Yang xiang, Xiaolong Wang
2015 Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)  
We treat the answer selection task as a sequence labeling problem and propose recurrent convolution neural networks to recognize good comments.  ...  In the recurrent architecture of our system, our approach uses 2-dimensional convolutional neural networks to learn the distributed representation for question-comment pair, and assigns the labels to the  ...  Recurrent Neural Network for comment sequence labeling Recurrent neural network is a straightforward adaptation of the standard feed-forward neural network (Bengio et al., 2012) to allow it to model  ... 
doi:10.18653/v1/s15-2037 dblp:conf/semeval/ZhouHLXW15 fatcat:nuzetkcpmbfh3mwwd5ytr5kr54

FuRongWang at SemEval-2017 Task 3: Deep Neural Networks for Selecting Relevant Answers in Community Question Answering

Sheng Zhang, Jiajun Cheng, Hui Wang, Xin Zhang, Pei Li, Zhaoyun Ding
2017 Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)  
We describe deep neural networks frameworks in this paper to address the community question answering (cQA) ranking task (SemEval-2017 task 3).  ...  Convolutional neural networks and bi-directional long-short term memory networks are applied in our methods to extract semantic information from questions and answers (comments).  ...  ., 2017) is the task for selecting relevant answers (or comments) for questions in community question answering (cQA).  ... 
doi:10.18653/v1/s17-2052 dblp:conf/semeval/ZhangCWZLD17 fatcat:hihaiofqu5bwdfprtbfkg27o4u

Chinese Medical Question Answer Matching Based on Interactive Sentence Representation Learning [article]

Xiongtao Cui, Jungang Han
2020 arXiv   pre-print
To better adapt to Chinese medical question-answer matching and take the advantages of different neural network structures, we propose the Crossed BERT network to extract the deep semantic information  ...  inside the sentence and the semantic association between question and answer, and then combine with the multi-scale CNNs network or BiGRU network to take the advantage of different structure of neural  ...  [25] proposed a hybrid model of CNN and GRU neural networks for Chinese medical question-answer selection.  ... 
arXiv:2011.13573v1 fatcat:ywed62aegrfxnb5pq3ux2ymyiu

Attention-based Pairwise Multi-Perspective Convolutional Neural Network for Answer Selection in Question Answering [article]

Jamshid Mozafari, Mohammad Ali Nematbakhsh, Afsaneh Fatemi
2019 arXiv   pre-print
The proposed model ranks the candidate answers in terms of semantic and syntactic similarity to the question, using convolutional neural networks.  ...  A component of these systems is Answer Selection which selects the most relevant from candidate answers.  ...  Thus, to be used in convolutional neural networks, the attention mechanism must be adapted to the convolutional neural network.  ... 
arXiv:1909.01059v3 fatcat:gv2i7hgzpnfldd6zqb3sztppt4

Open-Ended Long-form Video Question Answering via Adaptive Hierarchical Reinforced Networks

Zhou Zhao, Zhu Zhang, Shuwen Xiao, Zhou Yu, Jun Yu, Deng Cai, Fei Wu, Yueting Zhuang
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
decoder network to generate the natural language answer for open-ended video question answering.  ...  In this paper, we consider the problem of long-form video question answering from the viewpoint of adaptive hierarchical reinforced encoder-decoder network learning.  ...  supported by the National Natural Science Foundation of China under Grant No.61602405, No.61702143, No.61622205 and No.61472110, Sponsored by CCF-Tencent Open Research Fund and the China Knowledge Centre for  ... 
doi:10.24963/ijcai.2018/512 dblp:conf/ijcai/ZhaoZXYYCWZ18 fatcat:n6yvgkp54rh6hksn2yi6pxdoki

Learning a Natural Language Interface with Neural Programmer [article]

Arvind Neelakantan, Quoc V. Le, Martin Abadi, Andrew McCallum, Dario Amodei
2017 arXiv   pre-print
We enhance the objective function of Neural Programmer, a neural network with built-in discrete operations, and apply it on WikiTableQuestions, a natural language question-answering dataset.  ...  To our knowledge, this paper presents the first weakly supervised, end-to-end neural network model to induce such programs on a real-world dataset.  ...  Acknowledgements We are grateful to Panupong Pasupat for answering numerous questions about the dataset, and providing pre-processed version of the dataset and the output of the semantic parser.  ... 
arXiv:1611.08945v4 fatcat:th73j7sqtzgfrl6ogf72dj2lc4

EANN: Energy Adaptive Neural Networks

Salma Hassan, Sameh Attia, Khaled Nabil Salama, Hassan Mostafa
2020 Electronics  
This paper proposes an Energy Adaptive Feedforward Neural Network (EANN). It uses multiple approximation techniques in the hardware implementation of the neuron unit.  ...  The PDR technique enables the EANN system to remain functioning when the available energy budget is reduced by factors of 46.2% to 79.8% of the total energy of the unapproximated neural network.  ...  Figure 1 . 1 Basic structure of feedforward neural network. Figure 2 . 2 Limited-energy application block diagram for using energy adaptive neural networks.  ... 
doi:10.3390/electronics9050746 fatcat:4gi7wnkcozforlanwo6dnlgk3e
« Previous Showing results 1 — 15 out of 54,062 results