Using Abstraction Level in Question Answering System

Bei Xu; Xiaodong Wang; Hai Zhuge

doi:10.1109/SKG.2018.00040

Using Abstraction Level in Question Answering System

Bei Xu
, Xiaodong Wang
, Hai Zhuge

Nanjing University of Posts and Telecommunications

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

Traditional question answering systems extract answers in terms of the relevance between answer and question. However, when there are multiple relevant answers to a question, people usually use other dimensions besides relevance to select answers. Abstraction level is a frequently used dimension to distinguish general answer and specific answer. Previous question answering systems seldom consider the dimension. This paper proposes a way to calculate the abstraction level of answer. Experiments show that abstraction level can improve question answering in certain situations.

Original language	English
Title of host publication	Proceedings - 2018 14th International Conference on Semantics, Knowledge and Grids, SKG 2018
Publisher	IEEE
Pages	253-256
Number of pages	4
ISBN (Electronic)	9781728104416
DOIs	https://doi.org/10.1109/SKG.2018.00040
Publication status	Published - 2 May 2019
Event	14th International Conference on Semantics, Knowledge and Grids, SKG 2018 - Guangzhou, China Duration: 12 Sept 2018 → 14 Sept 2018

Publication series

Name	2018 14th International Conference on Semantics, Knowledge and Grids (SKG)
Publisher	IEEE
ISSN (Print)	2325-0623

Conference

Conference	14th International Conference on Semantics, Knowledge and Grids, SKG 2018
Country/Territory	China
City	Guangzhou
Period	12/09/18 → 14/09/18

Funding

ACKNOWLEDGMENT This research was supported by the National Natural Science Foundation of China (No. 61602256) and the Natural Science Foundation of Jiangsu (No. BK20150862).

Access to Document

10.1109/SKG.2018.00040

Cite this

@inproceedings{781dc50b26e84509845532fb75703368,

title = "Using Abstraction Level in Question Answering System",

abstract = "Traditional question answering systems extract answers in terms of the relevance between answer and question. However, when there are multiple relevant answers to a question, people usually use other dimensions besides relevance to select answers. Abstraction level is a frequently used dimension to distinguish general answer and specific answer. Previous question answering systems seldom consider the dimension. This paper proposes a way to calculate the abstraction level of answer. Experiments show that abstraction level can improve question answering in certain situations.",

author = "Bei Xu and Xiaodong Wang and Hai Zhuge",

year = "2019",

month = may,

day = "2",

doi = "10.1109/SKG.2018.00040",

language = "English",

series = "2018 14th International Conference on Semantics, Knowledge and Grids (SKG)",

publisher = "IEEE",

pages = "253--256",

booktitle = "Proceedings - 2018 14th International Conference on Semantics, Knowledge and Grids, SKG 2018",

address = "United States",

note = "14th International Conference on Semantics, Knowledge and Grids, SKG 2018 ; Conference date: 12-09-2018 Through 14-09-2018",

}

Xu, B, Wang, X & Zhuge, H 2019, Using Abstraction Level in Question Answering System. in Proceedings - 2018 14th International Conference on Semantics, Knowledge and Grids, SKG 2018., 8703959, 2018 14th International Conference on Semantics, Knowledge and Grids (SKG), IEEE, pp. 253-256, 14th International Conference on Semantics, Knowledge and Grids, SKG 2018, Guangzhou, China, 12/09/18. https://doi.org/10.1109/SKG.2018.00040

Using Abstraction Level in Question Answering System. / Xu, Bei; Wang, Xiaodong; Zhuge, Hai.
Proceedings - 2018 14th International Conference on Semantics, Knowledge and Grids, SKG 2018. IEEE, 2019. p. 253-256 8703959 (2018 14th International Conference on Semantics, Knowledge and Grids (SKG)).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - Using Abstraction Level in Question Answering System

AU - Xu, Bei

AU - Wang, Xiaodong

AU - Zhuge, Hai

PY - 2019/5/2

Y1 - 2019/5/2

N2 - Traditional question answering systems extract answers in terms of the relevance between answer and question. However, when there are multiple relevant answers to a question, people usually use other dimensions besides relevance to select answers. Abstraction level is a frequently used dimension to distinguish general answer and specific answer. Previous question answering systems seldom consider the dimension. This paper proposes a way to calculate the abstraction level of answer. Experiments show that abstraction level can improve question answering in certain situations.

AB - Traditional question answering systems extract answers in terms of the relevance between answer and question. However, when there are multiple relevant answers to a question, people usually use other dimensions besides relevance to select answers. Abstraction level is a frequently used dimension to distinguish general answer and specific answer. Previous question answering systems seldom consider the dimension. This paper proposes a way to calculate the abstraction level of answer. Experiments show that abstraction level can improve question answering in certain situations.

UR - https://www.scopus.com/pages/publications/85065795525

UR - https://ieeexplore.ieee.org/document/8703959

U2 - 10.1109/SKG.2018.00040

DO - 10.1109/SKG.2018.00040

M3 - Conference publication

AN - SCOPUS:85065795525

T3 - 2018 14th International Conference on Semantics, Knowledge and Grids (SKG)

SP - 253

EP - 256

BT - Proceedings - 2018 14th International Conference on Semantics, Knowledge and Grids, SKG 2018

PB - IEEE

T2 - 14th International Conference on Semantics, Knowledge and Grids, SKG 2018

Y2 - 12 September 2018 through 14 September 2018

ER -

Using Abstraction Level in Question Answering System

Abstract

Publication series

Conference

Funding

Access to Document

Other files and links

Fingerprint

Cite this