A Global–Local Attentive Relation Detection Model for Knowledge-Based Question Answering
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
A Global–Local Attentive Relation Detection Model for Knowledge-Based Question Answering. / Qiu, Chen; Zhou, Guangyou; Cai, Zhihua; Sogaard, Anders.
In: IEEE Transactions on Artificial Intelligence, Vol. 2, No. 2, 2021, p. 200-212.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - A Global–Local Attentive Relation Detection Model for Knowledge-Based Question Answering
AU - Qiu, Chen
AU - Zhou, Guangyou
AU - Cai, Zhihua
AU - Sogaard, Anders
PY - 2021
Y1 - 2021
N2 - Knowledge-based question answering (KBQA) is an essential but challenging task for artificial intelligence and natural language processing. A key challenge pertains to the design of effective algorithms for relation detection. Conventional methods model questions and candidate relations separately through the knowledge bases (KBs) without considering the rich word-level interactions between them. This approach may result in local optimal results. This article presents a global–local attentive relation detection model (GLAR) that utilizes the local module to learn the features of word-level interactions and employs the global module to acquire nonlinear relationships between questions and their candidate relations located in KBs. This article also reports on the application of an end-to-end retrieval-based KBQA system incorporating the proposed relation detection model. Experimental results obtained on two datasets demonstrated GLAR's remarkable performance in the relation detection tas...
AB - Knowledge-based question answering (KBQA) is an essential but challenging task for artificial intelligence and natural language processing. A key challenge pertains to the design of effective algorithms for relation detection. Conventional methods model questions and candidate relations separately through the knowledge bases (KBs) without considering the rich word-level interactions between them. This approach may result in local optimal results. This article presents a global–local attentive relation detection model (GLAR) that utilizes the local module to learn the features of word-level interactions and employs the global module to acquire nonlinear relationships between questions and their candidate relations located in KBs. This article also reports on the application of an end-to-end retrieval-based KBQA system incorporating the proposed relation detection model. Experimental results obtained on two datasets demonstrated GLAR's remarkable performance in the relation detection tas...
U2 - 10.1109/TAI.2021.3068697
DO - 10.1109/TAI.2021.3068697
M3 - Journal article
VL - 2
SP - 200
EP - 212
JO - IEEE Transactions on Artificial Intelligence
JF - IEEE Transactions on Artificial Intelligence
SN - 2691-4581
IS - 2
ER -
ID: 300671974