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 - http://www.scopus.com/inward/record.url?scp=85065795525&partnerID=8YFLogxK
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 -