Filters








22,361 Hits in 4.2 sec

Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access [article]

Seokhwan Kim, Mihail Eric, Karthik Gopalakrishnan, Behnam Hedayatnia, Yang Liu, Dilek Hakkani-Tur
2020 arXiv   pre-print
Our experimental results demonstrate the need for further research in this direction to enable more informative conversational systems.  ...  In this paper, we propose to expand coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources.  ...  dialogue systems to understand relevant domain knowledge, and generate system responses with the selected knowledge.  ... 
arXiv:2006.03533v1 fatcat:ye5lha24azhcdoyzjsprrzdbom

The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems [article]

Ryan Lowe, Nissan Pow, Iulian Serban, Joelle Pineau
2016 arXiv   pre-print
We also describe two neural learning architectures suitable for analyzing this dataset, and provide benchmark performance on the task of selecting the best next response.  ...  The dataset has both the multi-turn property of conversations in the Dialog State Tracking Challenge datasets, and the unstructured nature of interactions from microblog services such as Twitter.  ...  We would like to thank Laurent Charlin for his input into this paper, as well as Gabriel Forgues and Eric Crawford for interesting discussions.  ... 
arXiv:1506.08909v3 fatcat:swu6oxfehnhbdarczgixvljefe

A Survey of Document Grounded Dialogue Systems (DGDS) [article]

Longxuan Ma and Wei-Nan Zhang and Mingda Li and Ting Liu
2020 arXiv   pre-print
For example, movie discussion can change from chit-chat to QA, the conversational recommendation can transform from chit-chat to recommendation, etc.  ...  We believe that extracting unstructured document(s) information is the future trend of the DS because a great amount of human knowledge lies in these document(s).  ...  CONCLUSION The Document Grounded Dialogue System (DGDS) can mine document(s) information and discuss specific document(s) in a real human conversation.  ... 
arXiv:2004.13818v1 fatcat:euhtfpjccvestgfeimbmpc7fma

The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems

Ryan Lowe, Nissan Pow, Iulian Serban, Joelle Pineau
2015 Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue  
We also describe two neural learning architectures suitable for analyzing this dataset, and provide benchmark performance on the task of selecting the best next response.  ...  The dataset has both the multi-turn property of conversations in the Dialog State Tracking Challenge datasets, and the unstructured nature of interactions from microblog services such as Twitter.  ...  We would like to thank Laurent Charlin for his input into this paper, as well as Gabriel Forgues and Eric Crawford for interesting discussions.  ... 
doi:10.18653/v1/w15-4640 dblp:conf/sigdial/LowePSP15 fatcat:slgygxevtvatbnoarshtbaaz6e

QUERY-BASED SUMMARIZATION METHODS FOR CONVERSATIONAL AGENTS: AN OVERVIEW

Ketakee Nimavat
2017 International Journal of Advanced Research in Computer Science  
The paper hence explores various methods for summarization and focuses particularly on extracting the gist from the perspective of a given keyword i.e. query based summarization from raw unstructured text  ...  Along with that, the need for a proper framework to mine relevant knowledge from the said data is acknowledged and the challenges that a conversational agent would hence face are identified.  ...  Conversational Features: As text based algorithms pervade the space of human computer interaction, the systems will have to be more considerate of the expected features from a human companion such as spontaneity  ... 
doi:10.26483/ijarcs.v8i8.4788 fatcat:tc7jkg32dzem3hvpqt2ydq75iu

HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management [article]

Silin Gao, Ryuichi Takanobu, Wei Peng, Qun Liu, Minlie Huang
2021 arXiv   pre-print
However, they fall short of handling dialog turns grounded on unstructured knowledge (e.g. reviews and documents).  ...  Task-oriented dialog (TOD) systems typically manage structured knowledge (e.g. ontologies and databases) to guide the goal-oriented conversations.  ...  While in turns involving unstructured knowledge, the system manages a document base to retrieve relevant references for generating the response.  ... 
arXiv:2105.06041v2 fatcat:fb4gb3xs6jhcnif3yvvoqle4a4

Interactive Search on the Web: The Story So Far

Sareh Aghaei, Kevin Angele, Elwin Huaman, Geni Bushati, Mathias Schiestl, Anna Fensel
2022 Information  
As a subset of dialogue systems, chatbots try to simulate human-like conversations.  ...  As a subset of question answering systems, dialogue systems target to interact with human users through a dialog expressed in natural language.  ...  Another possible direction for future work is to focus on a relatively small time span (e.g., the latest ten years) and deepen the discussions and analysis of the literature.  ... 
doi:10.3390/info13070324 fatcat:3ynum6a2ozakjkyqtnf4qrvtji

Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs [article]

Zhibin Liu, Zheng-Yu Niu, Hua Wu, Haifeng Wang
2019 arXiv   pre-print
for knowledge selection decision, and texts can provide rich information for response generation.  ...  Two types of knowledge, triples from knowledge graphs and texts from documents, have been studied for knowledge aware open-domain conversation generation, in which graph paths can narrow down vertex candidates  ...  Acknowledgments We would like to thank the reviewers for their insightful comments. This work was supported by the Natural Science Foundation of China (No.61533018).  ... 
arXiv:1903.10245v4 fatcat:mg62euhxajgzxmifhvqv5fzovy

Natural Language Processing (NLP) and Its Impact across Industries – Unlocking the True Potential of Digital Healthcare (A Case Study Approach)

Sourajit Roy, Pankaj Pathak, S. Nithya
2021 Journal of Pharmaceutical Research International  
This causes a great deal of unstructured data to be processed that does not fit in with standard computational models.  ...  Natural Language Processing or NLP is one of their promising disciplines that has been increasingly dynamic via groundbreaking findings on most computer networks.  ...  ACKNOWLEDGEMENT The authors wish to acknowledge Symbiosis Institute of Management Studies for assisting & providing access to resources for this study.  ... 
doi:10.9734/jpri/2021/v33i35b31906 fatcat:awcitplqyrcf3pyz53wabos5pm

Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs

zhibin liu, Zheng-Yu Niu, Hua Wu, Haifeng Wang
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
for knowledge selection decision, and texts can provide rich information for response generation.  ...  Two types of knowledge, triples from knowledge graphs and texts from documents, have been studied for knowledge aware opendomain conversation generation, in which graph paths can narrow down vertex candidates  ...  Acknowledgments We would like to thank the reviewers for their insightful comments. This work was supported by the Natural Science Foundation of China (No.61533018).  ... 
doi:10.18653/v1/d19-1187 dblp:conf/emnlp/LiuNWW19 fatcat:j4j7lvsl6bgafgiykkbmltpray

Smart Assistance for Students and People Living in a Campus

Salvatore Gaglio, Giuseppe Lo Re, Marco Morana, Claudio Ruocco
2019 2019 IEEE International Conference on Smart Computing (SMARTCOMP)  
IBM Watson, for instance, is one of the most widely-adopted question-answering framework both because of its simplicity and accessibility through public APIs.  ...  Optionally, the content discovery module is called to extract relevant information from unstructured documents.  ...  Indeed, as for the conversational assistant, if it detects a wrong intent, it is required to choose the correct one and the system learns from its mistakes.  ... 
doi:10.1109/smartcomp.2019.00042 dblp:conf/smartcomp/GaglioRMR19 fatcat:euo75nqqzvb23eyyzfbvbgdgh4

Towards information-rich, logical text generation with knowledge-enhanced neural models [article]

Hao Wang, Bin Guo, Wei Wu, Zhiwen Yu
2020 arXiv   pre-print
The challenges of knowledge enhanced text generation including how to select the appropriate knowledge from large-scale knowledge bases, how to read and understand extracted knowledge, and how to integrate  ...  Text generation system has made massive promising progress contributed by deep learning techniques and has been widely applied in our life.  ...  The same query in human conversation may be related to different responses, so different knowledge may be utilized. To solve this problem, Lian et al.  ... 
arXiv:2003.00814v1 fatcat:5fllyakwqzf4vnmar3a6zjoewe

An assessment of email and spontaneous dialog visualizations

Marcus A. Butavicius, Michael D. Lee, Brandon M. Pincombe, Louise G. Mullen, Daniel J. Navarro, Kathryn M. Parsons, Agata McCormac
2012 International Journal of Human-Computer Studies  
Implications of these findings for real-world applications are discussed.  ...  by clicking on neighboring document representations.  ...  Assessing visualizations of unstructured text 38  ... 
doi:10.1016/j.ijhcs.2012.02.002 fatcat:2sf2nmnoznatfljdypuky7v2va

Cognitive Computing: What's in for Business Process Management? An Exploration of Use Case Ideas [chapter]

Maximilian Roeglinger, Johannes Seyfried, Simon Stelzl, Michael zur Muehlen
2018 Lecture Notes in Business Information Processing  
Cognitive Computing is expected to offer significant application opportunities for business process management (BPM).  ...  natural interaction of humans and machines.  ...  The data processing features of CC could enhance process mining techniques to leverage unstructured data (e.g., emails, conversations, or documents).  ... 
doi:10.1007/978-3-319-74030-0_32 fatcat:azsxlex2ozhabauqudauyhrglq

Towards Exploiting Background Knowledge for Building Conversation Systems

Nikita Moghe, Siddhartha Arora, Suman Banerjee, Mitesh M. Khapra
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
For example, it is common for humans to (involuntarily) produce utterances which are copied or suitably modified from background articles they have read about the topic.  ...  To facilitate the development of such natural conversation models which mimic the human process of conversing, we create a new dataset containing movie chats wherein each response is explicitly generated  ...  Acknowledgements We would like to thank Department of Computer Science and Engineering, and Robert Bosch Center for Data Sciences and Artificial Intelligence, IIT Madras (RBC-DSAI) for providing us with  ... 
doi:10.18653/v1/d18-1255 dblp:conf/emnlp/MogheABK18 fatcat:jaeanay7trdlbblqkezc2tkz7m
« Previous Showing results 1 — 15 out of 22,361 results