5 Hits in 4.2 sec

AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine

Minghui Qiu, Feng-Lin Li, Siyu Wang, Xing Gao, Yan Chen, Weipeng Zhao, Haiqing Chen, Jun Huang, Wei Chu
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
We propose AliMe Chat, an open-domain chatbot engine that integrates the joint results of Information Retrieval (IR) and Sequence to Sequence (Seq2Seq) based generation models.  ...  AliMe Chat uses an attentive Seq2Seq based rerank model to optimize the joint results. Extensive experiments show our engine outperforms both IR and generation based models.  ...  Acknowledgments The authors would like to thank Juwei Ren, Lanbo Li, Zhongzhou Zhao, Man Yuan, Qingqing Yu, Jun Yang and other members of Alibaba Cloud for helpful discussions and comments.  ... 
doi:10.18653/v1/p17-2079 dblp:conf/acl/QiuLWGCZCHC17 fatcat:2azoy3ag2jdkxohxb35olzudr4

AliMe Assist: An Intelligent Assistant for Creating an Innovative E-commerce Experience [article]

Feng-Lin Li, Minghui Qiu, Haiqing Chen, Xiongwei Wang, Xing Gao, Jun Huang, Juwei Ren, Zhongzhou Zhao, Weipeng Zhao, Lei Wang, Guwei Jin, Wei Chu
2018 arXiv   pre-print
Based on question answering (QA), AliMe Assist offers assistance service, customer service, and chatting service.  ...  It is able to take voice and text input, incorporate context to QA, and support multi-round interaction.  ...  To o er be er user experience, we build an open-domain chatbot engine, where we propose a hybrid approach that uses an a entive Sequence-to-Sequence (Seq2Seq) model to optimize the joint results of IR  ... 
arXiv:1801.05032v1 fatcat:nothcvv5k5hqbpfblmavpe6v3i

The Design and Implementation of Intelligent English Learning Chabot based on Transfer Learning Technology

Nuobei Shi, Qin Zeng, Raymond Shu Tak Lee
2021 Advances in Science, Technology and Engineering Systems  
Second is a converse special-domain and the highest third level is a language chatbot communication as freestyle conversation agent.  ...  In this paper, we proposed a Transfer-based English Language learning chatbot with three learning system levels for real-world application, which integrate recognition service from Google and GPT-2 Open  ...  Acknowledgment The authors would like to thank for UIC DST for the provision of computer equipment and facilities.  ... 
doi:10.25046/aj060505 fatcat:rpcvv2pzofgjnloausyhqve7i4

Towards Retrieval-based Conversational Recommendation [article]

Ahtsham Manzoor, Dietmar Jannach
2021 arXiv   pre-print
An alternative to such generation-based approaches is to retrieve responses from pre-recorded dialog data and to adapt them if needed.  ...  In this work, we re-assess the potential of such approaches and design and evaluate a novel technique for response retrieval and ranking.  ...  In this system, a sequence-to-sequence neural model is used to rerank a previously retrieved set of candidate responses.  ... 
arXiv:2109.02311v1 fatcat:jrbmijepfzdlpmoa4rsbzvmowi

Conversational Information Seeking [article]

Hamed Zamani, Johanne R. Trippas, Jeff Dalton, Filip Radlinski
Conversational information seeking (CIS) is concerned with a sequence of interactions between one or more users and an information system.  ...  Interactions in CIS are primarily based on natural language dialogue, while they may include other types of interactions, such as click, touch, and body gestures.  ...  This work was supported in part by the Center for Intelligent Information Retrieval, in part by an Alexa Prize grant from Amazon, and in part by an Engineering and Physical Sciences Research Council fellowship  ... 
doi:10.48550/arxiv.2201.08808 fatcat:l2fzanmuv5ezhpwkhvgbrjv63m