基于LSTM的集成网络增强聊天机器人长期依赖关系的学习

Q3 Mathematics
S. Patil, Venkatesh M. Mudaliar, P. Kamat, S. Gite
{"title":"基于LSTM的集成网络增强聊天机器人长期依赖关系的学习","authors":"S. Patil, Venkatesh M. Mudaliar, P. Kamat, S. Gite","doi":"10.1051/smdo/2020019","DOIUrl":null,"url":null,"abstract":"A chatbot is a software that can reproduce a discussion portraying a specific dimension of articulation among people and machines utilizing Natural Human Language. With the advent of AI, chatbots have developed from being minor guideline-based models to progressively modern models. A striking highlight of the current chatbot frameworks is their capacity to maintain and support explicit highlights and settings of the discussions empowering them to have human interaction in real-time surroundings. The paper presents a detailed database concerning the models utilized to deal with the learning of long haul conditions in a chatbot. The paper proposes a novel crossbreed Long Short Term Memory based Ensemble model to retain the information in specific situations. The proposed model uses a characterized number of Long Short Term Memory Networks as a significant aspect of its working as one to create the aggregate forecast class for the information inquiry and conversation. We found that both of the ensemble methods LSTM and GRU work well in different dataset environments and the ensemble technique is an effective one in chatbot applications.","PeriodicalId":37601,"journal":{"name":"International Journal for Simulation and Multidisciplinary Design Optimization","volume":"1 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1051/smdo/2020019","citationCount":"12","resultStr":"{\"title\":\"LSTM based Ensemble Network to enhance the learning of long-term dependencies in chatbot\",\"authors\":\"S. Patil, Venkatesh M. Mudaliar, P. Kamat, S. Gite\",\"doi\":\"10.1051/smdo/2020019\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A chatbot is a software that can reproduce a discussion portraying a specific dimension of articulation among people and machines utilizing Natural Human Language. With the advent of AI, chatbots have developed from being minor guideline-based models to progressively modern models. A striking highlight of the current chatbot frameworks is their capacity to maintain and support explicit highlights and settings of the discussions empowering them to have human interaction in real-time surroundings. The paper presents a detailed database concerning the models utilized to deal with the learning of long haul conditions in a chatbot. The paper proposes a novel crossbreed Long Short Term Memory based Ensemble model to retain the information in specific situations. The proposed model uses a characterized number of Long Short Term Memory Networks as a significant aspect of its working as one to create the aggregate forecast class for the information inquiry and conversation. We found that both of the ensemble methods LSTM and GRU work well in different dataset environments and the ensemble technique is an effective one in chatbot applications.\",\"PeriodicalId\":37601,\"journal\":{\"name\":\"International Journal for Simulation and Multidisciplinary Design Optimization\",\"volume\":\"1 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1051/smdo/2020019\",\"citationCount\":\"12\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal for Simulation and Multidisciplinary Design Optimization\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1051/smdo/2020019\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"Mathematics\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal for Simulation and Multidisciplinary Design Optimization","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1051/smdo/2020019","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Mathematics","Score":null,"Total":0}
引用次数: 12

摘要

聊天机器人是一种软件,它可以利用自然人类语言再现人与机器之间特定表达维度的讨论。随着人工智能的出现,聊天机器人已经从小型的基于指南的模型发展到逐渐现代化的模型。当前聊天机器人框架的一个引人注目的亮点是它们能够维护和支持明确的重点和讨论设置,使它们能够在实时环境中进行人类交互。本文给出了一个详细的数据库,其中包括用于处理聊天机器人长途条件学习的模型。本文提出了一种新的基于长短期记忆的集成模型,用于在特定情况下保留信息。该模型使用长短期记忆网络的特征数量作为其工作的一个重要方面,为信息查询和对话创建聚合预测类。我们发现LSTM和GRU两种集成方法在不同的数据集环境下都能很好地工作,集成技术在聊天机器人应用中是一种有效的集成技术。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
LSTM based Ensemble Network to enhance the learning of long-term dependencies in chatbot
A chatbot is a software that can reproduce a discussion portraying a specific dimension of articulation among people and machines utilizing Natural Human Language. With the advent of AI, chatbots have developed from being minor guideline-based models to progressively modern models. A striking highlight of the current chatbot frameworks is their capacity to maintain and support explicit highlights and settings of the discussions empowering them to have human interaction in real-time surroundings. The paper presents a detailed database concerning the models utilized to deal with the learning of long haul conditions in a chatbot. The paper proposes a novel crossbreed Long Short Term Memory based Ensemble model to retain the information in specific situations. The proposed model uses a characterized number of Long Short Term Memory Networks as a significant aspect of its working as one to create the aggregate forecast class for the information inquiry and conversation. We found that both of the ensemble methods LSTM and GRU work well in different dataset environments and the ensemble technique is an effective one in chatbot applications.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
2.00
自引率
0.00%
发文量
19
审稿时长
16 weeks
期刊介绍: The International Journal for Simulation and Multidisciplinary Design Optimization is a peer-reviewed journal covering all aspects related to the simulation and multidisciplinary design optimization. It is devoted to publish original work related to advanced design methodologies, theoretical approaches, contemporary computers and their applications to different fields such as engineering software/hardware developments, science, computing techniques, aerospace, automobile, aeronautic, business, management, manufacturing,... etc. Front-edge research topics related to topology optimization, composite material design, numerical simulation of manufacturing process, advanced optimization algorithms, industrial applications of optimization methods are highly suggested. The scope includes, but is not limited to original research contributions, reviews in the following topics: Parameter identification & Surface Response (all aspects of characterization and modeling of materials and structural behaviors, Artificial Neural Network, Parametric Programming, approximation methods,…etc.) Optimization Strategies (optimization methods that involve heuristic or Mathematics approaches, Control Theory, Linear & Nonlinear Programming, Stochastic Programming, Discrete & Dynamic Programming, Operational Research, Algorithms in Optimization based on nature behaviors,….etc.) Structural Optimization (sizing, shape and topology optimizations with or without external constraints for materials and structures) Dynamic and Vibration (cover modelling and simulation for dynamic and vibration analysis, shape and topology optimizations with or without external constraints for materials and structures) Industrial Applications (Applications Related to Optimization, Modelling for Engineering applications are very welcome. Authors should underline the technological, numerical or integration of the mentioned scopes.).
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信