An ensemble of retrieval-based and generation-based human-computer conversation systems

Yiping Song, Cheng-Te Li, Jian Yun Nie, Ming Zhang, Dongyan Zhao, Rui Yan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Human-computer conversation systems have attracted much attention in Natural Language Processing. Conversation systems can be roughly divided into two categories: retrieval-based and generation-based systems. Retrieval systems search a user-issued utterance (namely a query) in a large conversational repository and return a reply that best matches the query. Generative approaches synthesize new replies. Both ways have certain advantages but suffer from their own disadvantages. We propose a novel ensemble of retrieval-based and generation-based conversation system. The retrieved candidates, in addition to the original query, are fed to a reply generator via a neural network, so that the model is aware of more information. The generated reply together with the retrieved ones then participates in a re-ranking process to find the final reply to output. Experimental results show that such an ensemble system outperforms each single module by a large margin.

Original languageEnglish
Title of host publicationProceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018
EditorsJerome Lang
PublisherInternational Joint Conferences on Artificial Intelligence
Pages4382-4388
Number of pages7
ISBN (Electronic)9780999241127
Publication statusPublished - 2018 Jan 1
Event27th International Joint Conference on Artificial Intelligence, IJCAI 2018 - Stockholm, Sweden
Duration: 2018 Jul 132018 Jul 19

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
Volume2018-July
ISSN (Print)1045-0823

Other

Other27th International Joint Conference on Artificial Intelligence, IJCAI 2018
CountrySweden
CityStockholm
Period18-07-1318-07-19

Fingerprint

Computer systems
Neural networks
Processing

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Song, Y., Li, C-T., Nie, J. Y., Zhang, M., Zhao, D., & Yan, R. (2018). An ensemble of retrieval-based and generation-based human-computer conversation systems. In J. Lang (Ed.), Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018 (pp. 4382-4388). (IJCAI International Joint Conference on Artificial Intelligence; Vol. 2018-July). International Joint Conferences on Artificial Intelligence.
Song, Yiping ; Li, Cheng-Te ; Nie, Jian Yun ; Zhang, Ming ; Zhao, Dongyan ; Yan, Rui. / An ensemble of retrieval-based and generation-based human-computer conversation systems. Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. editor / Jerome Lang. International Joint Conferences on Artificial Intelligence, 2018. pp. 4382-4388 (IJCAI International Joint Conference on Artificial Intelligence).
@inproceedings{a5ba86f069eb471d936c2d49db0af77b,
title = "An ensemble of retrieval-based and generation-based human-computer conversation systems",
abstract = "Human-computer conversation systems have attracted much attention in Natural Language Processing. Conversation systems can be roughly divided into two categories: retrieval-based and generation-based systems. Retrieval systems search a user-issued utterance (namely a query) in a large conversational repository and return a reply that best matches the query. Generative approaches synthesize new replies. Both ways have certain advantages but suffer from their own disadvantages. We propose a novel ensemble of retrieval-based and generation-based conversation system. The retrieved candidates, in addition to the original query, are fed to a reply generator via a neural network, so that the model is aware of more information. The generated reply together with the retrieved ones then participates in a re-ranking process to find the final reply to output. Experimental results show that such an ensemble system outperforms each single module by a large margin.",
author = "Yiping Song and Cheng-Te Li and Nie, {Jian Yun} and Ming Zhang and Dongyan Zhao and Rui Yan",
year = "2018",
month = "1",
day = "1",
language = "English",
series = "IJCAI International Joint Conference on Artificial Intelligence",
publisher = "International Joint Conferences on Artificial Intelligence",
pages = "4382--4388",
editor = "Jerome Lang",
booktitle = "Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018",

}

Song, Y, Li, C-T, Nie, JY, Zhang, M, Zhao, D & Yan, R 2018, An ensemble of retrieval-based and generation-based human-computer conversation systems. in J Lang (ed.), Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. IJCAI International Joint Conference on Artificial Intelligence, vol. 2018-July, International Joint Conferences on Artificial Intelligence, pp. 4382-4388, 27th International Joint Conference on Artificial Intelligence, IJCAI 2018, Stockholm, Sweden, 18-07-13.

An ensemble of retrieval-based and generation-based human-computer conversation systems. / Song, Yiping; Li, Cheng-Te; Nie, Jian Yun; Zhang, Ming; Zhao, Dongyan; Yan, Rui.

Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. ed. / Jerome Lang. International Joint Conferences on Artificial Intelligence, 2018. p. 4382-4388 (IJCAI International Joint Conference on Artificial Intelligence; Vol. 2018-July).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - An ensemble of retrieval-based and generation-based human-computer conversation systems

AU - Song, Yiping

AU - Li, Cheng-Te

AU - Nie, Jian Yun

AU - Zhang, Ming

AU - Zhao, Dongyan

AU - Yan, Rui

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Human-computer conversation systems have attracted much attention in Natural Language Processing. Conversation systems can be roughly divided into two categories: retrieval-based and generation-based systems. Retrieval systems search a user-issued utterance (namely a query) in a large conversational repository and return a reply that best matches the query. Generative approaches synthesize new replies. Both ways have certain advantages but suffer from their own disadvantages. We propose a novel ensemble of retrieval-based and generation-based conversation system. The retrieved candidates, in addition to the original query, are fed to a reply generator via a neural network, so that the model is aware of more information. The generated reply together with the retrieved ones then participates in a re-ranking process to find the final reply to output. Experimental results show that such an ensemble system outperforms each single module by a large margin.

AB - Human-computer conversation systems have attracted much attention in Natural Language Processing. Conversation systems can be roughly divided into two categories: retrieval-based and generation-based systems. Retrieval systems search a user-issued utterance (namely a query) in a large conversational repository and return a reply that best matches the query. Generative approaches synthesize new replies. Both ways have certain advantages but suffer from their own disadvantages. We propose a novel ensemble of retrieval-based and generation-based conversation system. The retrieved candidates, in addition to the original query, are fed to a reply generator via a neural network, so that the model is aware of more information. The generated reply together with the retrieved ones then participates in a re-ranking process to find the final reply to output. Experimental results show that such an ensemble system outperforms each single module by a large margin.

UR - http://www.scopus.com/inward/record.url?scp=85051552057&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051552057&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85051552057

T3 - IJCAI International Joint Conference on Artificial Intelligence

SP - 4382

EP - 4388

BT - Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018

A2 - Lang, Jerome

PB - International Joint Conferences on Artificial Intelligence

ER -

Song Y, Li C-T, Nie JY, Zhang M, Zhao D, Yan R. An ensemble of retrieval-based and generation-based human-computer conversation systems. In Lang J, editor, Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. International Joint Conferences on Artificial Intelligence. 2018. p. 4382-4388. (IJCAI International Joint Conference on Artificial Intelligence).