Filters








33,578 Hits in 17.1 sec

Improving Response Selection in Multi-Turn Dialogue Systems by Incorporating Domain Knowledge [article]

Debanjan Chaudhuri, Agustinus Kristiadi, Jens Lehmann, Asja Fischer
2018 arXiv   pre-print
This work proposes a novel neural network architecture for response selection in an end-to-end multi-turn conversational dialogue setting.  ...  Experimental results show that our model outperforms all other state-of-the-art methods for response selection in multi-turn conversations.  ...  selection in a multi-turn setting.  ... 
arXiv:1809.03194v3 fatcat:udl4hlmkyzembenevdxq572rry

Improving Response Selection in Multi-Turn Dialogue Systems by Incorporating Domain Knowledge

Debanjan Chaudhuri, Agustinus Kristiadi, Jens Lehmann, Asja Fischer
2018 Proceedings of the 22nd Conference on Computational Natural Language Learning  
This work proposes a novel neural network architecture for response selection in an end-to-end multi-turn conversational dialogue setting.  ...  Experimental results show that our model outperforms all other state-of-the-art methods for response selection in multi-turn conversations.  ...  selection in a multi-turn setting.  ... 
doi:10.18653/v1/k18-1048 dblp:conf/conll/ChaudhuriKLF18 fatcat:jjuvrtm75jde7okfpiyz6gf2sq

Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots [article]

Jia-Chen Gu, Tianda Li, Quan Liu, Zhen-Hua Ling, Zhiming Su, Si Wei, Xiaodan Zhu
2020 arXiv   pre-print
Finally, domain adaptation is performed to incorporate the in-domain knowledge into pre-trained language models.  ...  In this paper, we study the problem of employing pre-trained language models for multi-turn response selection in retrieval-based chatbots.  ...  To incorporate specific in-domain knowledge, adaptation on in-domain corpora are designed.  ... 
arXiv:2004.03588v2 fatcat:btgduwait5dwpiulmenie3qh64

UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues [article]

Hung Le, Doyen Sahoo, Chenghao Liu, Nancy F. Chen, Steven C.H. Hoi
2020 arXiv   pre-print
Unlike the existing approaches that are often designed to train each module separately, we propose "UniConv" -- a novel unified neural architecture for end-to-end conversational systems in multi-domain  ...  Dialogue Act and Response Generator which incorporates information from various input components and models dialogue acts and target responses simultaneously.  ...  The first author of this paper is supported by the Agency for Science, Technology and Research (A*STAR) Computing and Information Science scholarship.  ... 
arXiv:2004.14307v2 fatcat:resbk6yaercebanfrbhpypmvmq

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.  ...  Keeping the conversation consistent and avoiding its repetition are two key factors to construct an intelligent multi-turn knowledge-grounded dialogue system.  ...  Acknowledgements This work is supported by the National Key Research and Development Programs (Grant No.2017YFB0803301).  ... 
doi:10.1609/aaai.v34i05.6425 fatcat:vfhq4lvm65gfhdsjlvkaq4mmuq

Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey [article]

Jinjie Ni, Tom Young, Vlad Pandelea, Fuzhao Xue, Erik Cambria
2022 arXiv   pre-print
From the angle of system type, we discuss task-oriented and open-domain dialogue systems as two streams of research, providing insight into the hot topics related.  ...  In this survey, we mainly focus on the deep learning based dialogue systems.  ...  Acknowledgements This research/project is supported by A*STAR under its Industry Alignment Fund (LOA Award I1901E0046).  ... 
arXiv:2105.04387v5 fatcat:yd3gqg45rjgzxbiwfdlcvf3pye

Towards Task-Oriented Dialogue in Mixed Domains [article]

Tho Luong Chi, Phuong Le-Hong
2019 arXiv   pre-print
We study the effect of alternating between different domains in sequences of dialogue turns using two related state-of-the-art dialogue systems.  ...  We then propose a hybrid system which is able to improve the belief tracking accuracy of about 28% of average absolute point on a standard multi-domain dialogue dataset.  ...  In this mixed-domain dialogue, there is a turn in the weather domain, followed by a turn in POI domain or vice versa. We call this dataset the sequential turn dataset.  ... 
arXiv:1909.02265v1 fatcat:wbiyr5mpw5d2lilmnpdrj6odsa

A Survey on Dialogue Systems: Recent Advances and New Frontiers [article]

Hongshen Chen, Xiaorui Liu, Dawei Yin, Jiliang Tang
2018 arXiv   pre-print
In this article, we give an overview to these recent advances on dialogue systems from various perspectives and discuss some possible research directions.  ...  Recent advances on dialogue systems are overwhelmingly contributed by deep learning techniques, which have been employed to enhance a wide range of big data applications such as computer vision, natural  ...  Multi-turn Response Matching In recent years, multi-turn retrieval-based conversation draws more and more attention.  ... 
arXiv:1711.01731v3 fatcat:6wuovcynqbhlzmuorchn4mn6ma

DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation [article]

Md Rashad Al Hasan Rony, Ricardo Usbeck, Jens Lehmann
2022 arXiv   pre-print
facilitate the system selecting relevant information during the dialogue generation.  ...  Specifically, we propose DialoKG, a novel task-oriented dialogue system that effectively incorporates knowledge into a language model.  ...  The authors also acknowledge the financial support by the Federal Ministry for Economic Affairs and Energy of Germany in the project CoyPu (project number 01MK21007G).  ... 
arXiv:2204.09149v1 fatcat:sccjfvje4fbqxj675pj3olpvmq

KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation [article]

Hao Zhou, Chujie Zheng, Kaili Huang, Minlie Huang, Xiaoyan Zhu
2020 arXiv   pre-print
In this paper, we propose a Chinese multi-domain knowledge-driven conversation dataset, KdConv, which grounds the topics in multi-turn conversations to knowledge graphs.  ...  The research of knowledge-driven conversational systems is largely limited due to the lack of dialog data which consist of multi-turn conversations on multiple topics and with knowledge annotations.  ...  Acknowledgments This work was jointly supported by the NSFC projects (Key project with No. 61936010 and regular project with No. 61876096), and the National Key R&D Program of China (Grant No. 2018YFC0830200  ... 
arXiv:2004.04100v1 fatcat:g6tqgjrhunc7pnsdvhsxxx5iuq

Dialogue History Matters! Personalized Response Selectionin Multi-turn Retrieval-based Chatbots [article]

Juntao Li, Chang Liu, Chongyang Tao, Zhangming Chan, Dongyan Zhao, Min Zhang, Rui Yan
2021 arXiv   pre-print
Existing multi-turn context-response matching methods mainly concentrate on obtaining multi-level and multi-dimension representations and better interactions between context utterances and response.  ...  To fill the gap between these up-to-date methods and the real-world applications, we incorporate user-specific dialogue history into the response selection and propose a personalized hybrid matching network  ...  ACKNOWLEDGMENTS We would like to thank the efforts of anonymous reviewers for improving this paper.  ... 
arXiv:2103.09534v1 fatcat:oy6xk7jzdzgrhnwmmx753inuhu

Sequential Neural Networks for Noetic End-to-End Response Selection

Qian Chen, Wen Wang
2020 Computer Speech and Language  
In this paper, we investigate a sequential matching model based only on chain sequence for multi-turn response selection.  ...  Our results demonstrate that the potentials of sequential matching approaches have not yet been fully exploited in the past for multi-turn response selection.  ...  the efficacy of the ESIM model on multi-turn response selection for multi-domain multi-turn dialogues or even multi-modal dialogues. (3) We plan to investigate the effectiveness of applying the ESIM model  ... 
doi:10.1016/j.csl.2020.101072 fatcat:on6rdijknzax7bhda46te2z3xy

Can I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modeling [article]

Di Jin, Seokhwan Kim, Dilek Hakkani-Tur
2021 arXiv   pre-print
Our approach works in a pipelined manner with knowledge-seeking turn detection, knowledge selection, and response generation in sequence.  ...  This work focuses on responding to these beyond-API-coverage user turns by incorporating external, unstructured knowledge sources.  ...  Domain Classification In multi-domain conversations, if the system knows what domain a given turn belongs to, the search space for knowledge selection can be greatly reduced by taking the domain-specific  ... 
arXiv:2106.09174v1 fatcat:jesri2izlbcxvedyllqta7nqwe

Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset and Benchmark [article]

Zhengcong Fei, Zekang Li, Jinchao Zhang, Yang Feng, Jie Zhou
2021 arXiv   pre-print
However, most current dialogue researches focus on text-only dialogue tasks. In this paper, we propose a new task named as Meme incorporated Open-domain Dialogue (MOD).  ...  To facilitate the MOD research, we construct a large-scale open-domain multimodal dialogue dataset incorporating abundant Internet memes into utterances.  ...  Even though there is an increasing interest in chatbots that can converse with humans using multiple modalities, incorporating contextualized Internet memes into multi-turn open-domain dialogues under  ... 
arXiv:2109.01839v1 fatcat:p2zd2drhcrfcrlmw23nka7jt3m

A Framework for Building Closed-Domain Chat Dialogue Systems [article]

Mikio Nakano, Kazunori Komatani
2020 arXiv   pre-print
Being able to engage in chat dialogues has been found effective for improving communication between humans and dialogue systems.  ...  This paper focuses on closed-domain systems because they would be useful when combined with task-oriented dialogue systems in the same domain.  ...  This is achieved by employing a multi-expert model [10] as explained in Section 3.1. Using HRIChat, we have built FoodChatbot, an application in the food and restaurant domain.  ... 
arXiv:1910.13826v3 fatcat:ih75il7yorcizmvsmzlyo5bimy
« Previous Showing results 1 — 15 out of 33,578 results