Principle-based approach for semi-Automatic construction of a restaurant question answering system from limited datasets

Ting Hao Yang; Yu Lun Hsieh; Youshan Chung; Cheng Wei Shih; Shih Hung Liu; Yung Chun Chang; Wen Lian Hsu

doi:10.1109/IRI.2016.77

Principle-based approach for semi-Automatic construction of a restaurant question answering system from limited datasets

Ting Hao Yang, Yu Lun Hsieh, Youshan Chung, Cheng Wei Shih, Shih Hung Liu, Yung Chun Chang, Wen Lian Hsu

研究成果: 書貢獻/報告類型 › 會議貢獻

1 引文斯高帕斯（Scopus）

摘要

Question answering (QA) is an important research issue in natural language processing, and most state-of-the-Art question answering systems are based on statistical models. After wit nessing recent achievements in ArtfIcial Intelligent (Al), many businesses wish to apply those techniques to an automatic QA system that is capable of providing 24-hour customer services for their clients. However, o ne imminent problem is the lack of labeled training data for the specfIc domain. To address this issue, we propose to combine a knowledge-based approach and an automatic principle generation process to build a QA system from limited resources. Experiments conducted on a Mandarin Restaurant dataset show that our system achieves an average accuracy of 44% for 10 question types. It demonstrates that our approach can provide an effective tool when creating a QA system.

原文	英語
主出版物標題	Proceedings - 2016 IEEE 17th International Conference on Information Reuse and Integration, IRI 2016
發行者	Institute of Electrical and Electronics Engineers Inc.
頁面	520-524
頁數	5
ISBN（電子）	9781509032075
DOIs	https://doi.org/10.1109/IRI.2016.77
出版狀態	已發佈 - 2016
對外發佈	是
事件	17th IEEE International Conference on Information Reuse and Integration, IRI 2016 - Pittsburgh, 美国持續時間: 7月 28 2016 → 7月 30 2016

會議

會議	17th IEEE International Conference on Information Reuse and Integration, IRI 2016
國家/地區	美国
城市	Pittsburgh
期間	7/28/16 → 7/30/16

ASJC Scopus subject areas

資訊系統
資訊系統與管理

存取文件

10.1109/IRI.2016.77

其它文件與鏈接

引用此

Yang, T. H., Hsieh, Y. L., Chung, Y., Shih, C. W., Liu, S. H., Chang, Y. C., & Hsu, W. L. (2016). Principle-based approach for semi-Automatic construction of a restaurant question answering system from limited datasets. 於 Proceedings - 2016 IEEE 17th International Conference on Information Reuse and Integration, IRI 2016 (頁 520-524). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IRI.2016.77

Principle-based approach for semi-Automatic construction of a restaurant question answering system from limited datasets. / Yang, Ting Hao; Hsieh, Yu Lun; Chung, Youshan 等.
Proceedings - 2016 IEEE 17th International Conference on Information Reuse and Integration, IRI 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 520-524.

研究成果: 書貢獻/報告類型 › 會議貢獻

Yang, TH, Hsieh, YL, Chung, Y, Shih, CW, Liu, SH, Chang, YC & Hsu, WL 2016, Principle-based approach for semi-Automatic construction of a restaurant question answering system from limited datasets. 於 Proceedings - 2016 IEEE 17th International Conference on Information Reuse and Integration, IRI 2016. Institute of Electrical and Electronics Engineers Inc., 頁 520-524, 17th IEEE International Conference on Information Reuse and Integration, IRI 2016, Pittsburgh, 美国, 7/28/16. https://doi.org/10.1109/IRI.2016.77

Yang TH, Hsieh YL, Chung Y, Shih CW, Liu SH, Chang YC 等. Principle-based approach for semi-Automatic construction of a restaurant question answering system from limited datasets. 於 Proceedings - 2016 IEEE 17th International Conference on Information Reuse and Integration, IRI 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 520-524 doi: 10.1109/IRI.2016.77

@inproceedings{198fdc23152a43808ff053861e57c503,

title = "Principle-based approach for semi-Automatic construction of a restaurant question answering system from limited datasets",

abstract = "Question answering (QA) is an important research issue in natural language processing, and most state-of-the-Art question answering systems are based on statistical models. After wit nessing recent achievements in ArtfIcial Intelligent (Al), many businesses wish to apply those techniques to an automatic QA system that is capable of providing 24-hour customer services for their clients. However, o ne imminent problem is the lack of labeled training data for the specfIc domain. To address this issue, we propose to combine a knowledge-based approach and an automatic principle generation process to build a QA system from limited resources. Experiments conducted on a Mandarin Restaurant dataset show that our system achieves an average accuracy of 44% for 10 question types. It demonstrates that our approach can provide an effective tool when creating a QA system.",

keywords = "Alignment, Dominating Set, Ontology",

author = "Yang, {Ting Hao} and Hsieh, {Yu Lun} and Youshan Chung and Shih, {Cheng Wei} and Liu, {Shih Hung} and Chang, {Yung Chun} and Hsu, {Wen Lian}",

year = "2016",

doi = "10.1109/IRI.2016.77",

language = "English",

pages = "520--524",

booktitle = "Proceedings - 2016 IEEE 17th International Conference on Information Reuse and Integration, IRI 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "17th IEEE International Conference on Information Reuse and Integration, IRI 2016 ; Conference date: 28-07-2016 Through 30-07-2016",

}

TY - GEN

T1 - Principle-based approach for semi-Automatic construction of a restaurant question answering system from limited datasets

AU - Yang, Ting Hao

AU - Hsieh, Yu Lun

AU - Chung, Youshan

AU - Shih, Cheng Wei

AU - Liu, Shih Hung

AU - Chang, Yung Chun

AU - Hsu, Wen Lian

PY - 2016

Y1 - 2016

N2 - Question answering (QA) is an important research issue in natural language processing, and most state-of-the-Art question answering systems are based on statistical models. After wit nessing recent achievements in ArtfIcial Intelligent (Al), many businesses wish to apply those techniques to an automatic QA system that is capable of providing 24-hour customer services for their clients. However, o ne imminent problem is the lack of labeled training data for the specfIc domain. To address this issue, we propose to combine a knowledge-based approach and an automatic principle generation process to build a QA system from limited resources. Experiments conducted on a Mandarin Restaurant dataset show that our system achieves an average accuracy of 44% for 10 question types. It demonstrates that our approach can provide an effective tool when creating a QA system.

AB - Question answering (QA) is an important research issue in natural language processing, and most state-of-the-Art question answering systems are based on statistical models. After wit nessing recent achievements in ArtfIcial Intelligent (Al), many businesses wish to apply those techniques to an automatic QA system that is capable of providing 24-hour customer services for their clients. However, o ne imminent problem is the lack of labeled training data for the specfIc domain. To address this issue, we propose to combine a knowledge-based approach and an automatic principle generation process to build a QA system from limited resources. Experiments conducted on a Mandarin Restaurant dataset show that our system achieves an average accuracy of 44% for 10 question types. It demonstrates that our approach can provide an effective tool when creating a QA system.

KW - Alignment

KW - Dominating Set

KW - Ontology

UR - http://www.scopus.com/inward/record.url?scp=84991269164&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991269164&partnerID=8YFLogxK

U2 - 10.1109/IRI.2016.77

DO - 10.1109/IRI.2016.77

M3 - Conference contribution

AN - SCOPUS:84991269164

SP - 520

EP - 524

BT - Proceedings - 2016 IEEE 17th International Conference on Information Reuse and Integration, IRI 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th IEEE International Conference on Information Reuse and Integration, IRI 2016

Y2 - 28 July 2016 through 30 July 2016

ER -

Principle-based approach for semi-Automatic construction of a restaurant question answering system from limited datasets

摘要

會議

ASJC Scopus subject areas

存取文件

其它文件與鏈接

指紋

引用此