21,489 Hits in 9.5 sec

Explainable Neural Computation via Stack Neural Module Networks

Ronghang Hu, Jacob Andreas, Trevor Darrell, Kate Saenko
2021 Applied AI Letters  
In complex inferential tasks like question answering, machine learning models must confront two challenges: the need to implement a compositional reasoning process, and, in many applications, the need  ...  for this reasoning process to be interpretable to assist users in both development and prediction.  ...  A variety of different model architectures have been proposed for complex reasoning and question answering.  ... 
doi:10.1002/ail2.39 fatcat:o54xfuyapze75f545qznkn5ng4

Hybrid CNN-LSTM Model for Answer Identification

2019 International journal of recent technology and engineering  
User quest for information has led to development of Question Answer (QA) system to provide relevant answers to user questions.  ...  The paper proposes a hybrid model to identify suitable answer for posed question.  ...  LITERATURE REVIEW In 2018, Zhou et al. [1] have suggested a recurrent convolutional neural network (RCNN) scheme for selecting answers in community question answering (CQA).  ... 
doi:10.35940/ijrte.c4281.098319 fatcat:manqnd4r75b33c2dasxt6nvyxe

Learning to Reason on Tree Structures for Knowledge-Based Visual Question Answering

Qifeng Li, Xinyi Tang, Yi Jian
2022 Sensors  
Collaborative reasoning for knowledge-based visual question answering is challenging but vital and efficient in understanding the features of the images and questions.  ...  For conducting visual reasoning on all kinds of image–question pairs, in this paper, we propose a novel reasoning model of a question-guided tree structure with a knowledge base (QGTSKB) for addressing  ...  How to deeply mine object relationships in images to establish a graph neural network for reasoning on visual question answering is essential.  ... 
doi:10.3390/s22041575 pmid:35214484 pmcid:PMC8874875 fatcat:sorjkavo4rcv7hjyuzmhjzmiai

Identifying Experts in Community Question Answering Website Based on Graph Convolutional Neural Network

Chen Liu, Yuchen Hao, Wei Shan, Zhihong Dai
2020 IEEE Access  
For community question answering (CQA) websites, the community structure makes it easier for users with similar interests to gather together.  ...  expert finding.  ... 
doi:10.1109/access.2020.3012553 fatcat:vjxbd2ocx5ev7kg7shctmqxyee

Support-BERT: Predicting Quality of Question-Answer Pairs in MSDN using Deep Bidirectional Transformer [article]

Bhaskar Sen, Nikhil Gopal, Xinwei Xue
2020 arXiv   pre-print
However, there is a lack of an integrated question-answer quality model for community question answering websites in the literature.  ...  Quality of questions and answers from community support websites (e.g.  ...  [10] proposed to solve the quality model by finding best expert users for directing the questions for answer.  ... 
arXiv:2005.08294v1 fatcat:wsn5xw7rmfgjle3vewzppl27l4

Towards a Multi-View Attentive Matching for Personalized Expert Finding

Qiyao Peng, Hongtao Liu, Yinghui Wang, Hongyan Xu, Pengfei Jiao, Minglai Shao, Wenjun Wang
2022 Proceedings of the ACM Web Conference 2022  
In Community Question Answering (CQA) websites, expert finding aims at seeking suitable experts to answer questions.  ...  In the intra-view encoder, we design an interactive attention network to capture the view-specific relevance between the target question and the historical answered questions of experts for all different  ...  ACKNOWLEDGMENTS This work was supported by the Sustainable Development Project of Shenzhen (KCXFZ20201221173013036), State Key Laboratory of Communication Content Cognition (A32002), the China Postdoctoral  ... 
doi:10.1145/3485447.3512086 fatcat:kpyaysvffjayhonrc6i6rzx4cm

Question-Aware Memory Network for Multi-hop Question Answering in Human-Robot Interaction [article]

Xinmeng Li, Mamoun Alazab, Qian Li, Keping Yu, Quanjun Yin
2021 arXiv   pre-print
To solve this problem, we propose question-aware memory network for multi-hop question answering, named QA2MN, to update the attention on question timely in the reasoning process.  ...  For the multi-relation question with higher variety and complexity, the tokens of the question have different priority for the triples selection in the reasoning steps.  ...  We implement the architecture with key-value memory neural network, named QA2MN (Question-Aware Memory Network for Question Answering), to update the attention on question timely during reasoning.  ... 
arXiv:2104.13173v1 fatcat:3v43jnf74rfyzi2x54df7vpk5i

Compositional Attention Networks for Machine Reasoning [article]

Drew A. Hudson, Christopher D. Manning
2018 arXiv   pre-print
The model approaches problems by decomposing them into a series of attention-based reasoning steps, each performed by a novel recurrent Memory, Attention, and Composition (MAC) cell that maintains a separation  ...  We present the MAC network, a novel fully differentiable neural network architecture, designed to facilitate explicit and expressive reasoning.  ...  image (knowledge base) and aggregate the results into a recurrent memory. (3) The output classifier computes the final answer using the question and the final memory state. to perform explicit and sound  ... 
arXiv:1803.03067v2 fatcat:xmahwu3klncu5jhwnjggno7u3m

Sentence Completion using NLP Techniques

Umang Rupareliya
2019 International Journal for Research in Applied Science and Engineering Technology  
In this paper, we plan to apply and compare various approaches for automated sentence completion which include Latent Semantic Indexing and Recurrent Neural Networks.  ...  the method using local information (Recurrent Neural Network).  ...  ACKNOWLEDGEMENT We would like to thank all the members who helped investing their time on our project, and also we would like to express gratitude to the entire 'anonymous' expert for their insights on  ... 
doi:10.22214/ijraset.2019.4474 fatcat:hslskodrf5dppagxj44kk6ynma

Adaptive Memory Networks [article]

Daniel Li, Asim Kadav
2018 arXiv   pre-print
We present Adaptive Memory Networks (AMN) that processes input-question pairs to dynamically construct a network architecture optimized for lower inference times for Question Answering (QA) tasks.  ...  AMN processes the input story to extract entities and stores them in memory banks.  ...  We find that our network is able to reason useful entities for both tasks and store them in the final memory bank.  ... 
arXiv:1802.00510v1 fatcat:mnevmuf7mrgvxp7t5dwwdb4s7m

Question Retrieval for Community-based Question Answering via Heterogeneous Network Integration Learning [article]

Zheqian Chen and Chi Zhang and Zhou Zhao and Deng Cai
2016 arXiv   pre-print
Community based question answering platforms have attracted substantial users to share knowledge and learn from each other.  ...  It is urgent for us to take effective automated algorithms to reuse historical questions with corresponding answers.  ...  CONCLUSION Question retrieval is an essential component in Community Question Answering(CQA) services.  ... 
arXiv:1611.08135v1 fatcat:vptyyihojbgnvg2zgbys6c5loq


2004 Advances in Fuzzy Systems — Applications and Theory  
Several experts have made interesting comments on the most challenging problems.  ...  Acknowledgments We would like to thank our expert colleagues who supported this project by sending descriptions of problems that according to them are the most challenging issues in the field of computational  ...  Is this approximation sufficient to replace dynamical networks with spiking neurons or recurrent networks? What are the limitations? Many questions are still to be answered.  ... 
doi:10.1142/9789812562531_0001 fatcat:lk3kdecperbt3aynsbd7jnqsoe

Learning Decision Trees Recurrently Through Communication

Stephan Alaniz, Diego Marcos, Bernt Schiele, Zeynep Akata
2021 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
reasonable period of time after the work was first published, provided that clear reference is made to the source of the first publication of the work.  ...  Article 25fa states that the author of a short scientific work funded either wholly or partially by Dutch public funds is entitled to make that work publicly available for no consideration following a  ...  Recurrent Decision Tree (RDT) Model RDT consists of three parts: an explicit memory M, an LSTM [24] , and a question-decoder module, Question MLP (see Figure 2 (left)).  ... 
doi:10.1109/cvpr46437.2021.01331 fatcat:77washmnijc5bjgnzzccn5qnoe

Towards Smart e-Infrastructures, A Community Driven Approach Based on Real Datasets [article]

Prashant Singh, Mona Mohamed Elamin, Salman Toor
2020 arXiv   pre-print
However, efficient utilization of resources in data centers remains a challenging task, mainly due to the complexity of managing physical nodes, network equipment, cooling systems, electricity, etc.  ...  This article presents a community-driven open source software framework that allows community members to develop better understanding of various aspects of resource utilization.  ...  We would also like to thanks UPPMAX [15] and CSC [14] for providing us the valuable datasets.  ... 
arXiv:2012.09579v1 fatcat:6culoz52vndpbg5r6r7awsrs4a

Visual Question Answering: A Survey of Methods and Datasets [article]

Qi Wu, Damien Teney, Peng Wang, Chunhua Shen, Anthony Dick, Anton van den Hengel
2016 arXiv   pre-print
In particular, we examine the common approach of combining convolutional and recurrent neural networks to map images and questions to a common feature space.  ...  Given an image and a question in natural language, it requires reasoning over visual elements of the image and general knowledge to infer the correct answer.  ...  Acknowledgements This research was in part supported by the Data to Decisions Cooperative Research Centre funded by the Australian Government.  ... 
arXiv:1607.05910v1 fatcat:ijh4zruldjhwxpbuwulpyogsxy
« Previous Showing results 1 — 15 out of 21,489 results