MemTimes: Temporal Scoping of Facts with Memory Network

Siyuan Cao; Qiang Yang; Zhixu Li; Guanfeng Liu; Detian Zhang; Jiajie Xu

doi:10.1007/978-3-030-59419-0_5

MemTimes: Temporal Scoping of Facts with Memory Network

Siyuan Cao, Qiang Yang, Zhixu Li, Guanfeng Liu, Detian Zhang, Jiajie Xu

King Abdullah University of Science and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper works on temporal scoping, i.e., adding time interval to facts in Knowledge Bases (KBs). The existing methods for temporal scope inference and extraction still suffer from low accuracy. In this paper, we propose a novel neural model based on Memory Network to do temporal reasoning among sentences for the purpose of temporal scoping. We design proper ways to encode both semantic and temporal information contained in the mention set of each fact, which enables temporal reasoning with Memory Network. We also find ways to remove the effect brought by noisy sentences, which can further improve the robustness of our approach. The experiments show that this solution is highly effective for detecting temporal scope of facts.

Original language	English (US)
Title of host publication	Database Systems for Advanced Applications
Publisher	Springer International Publishing
Pages	70-86
Number of pages	17
ISBN (Print)	9783030594183
DOIs	https://doi.org/10.1007/978-3-030-59419-0_5
State	Published - Sep 21 2020

Bibliographical note

KAUST Repository Item: Exported on 2020-10-15
Acknowledgements: This research is partially supported by Natural Science Foundation of Jiangsu Province (No. BK20191420), National Natural Science Foundation of China (Grant No. 61632016, 61572336, 61572335, 61772356), Natural Science Research Project of Jiangsu Higher Education Institution (No. 17KJA520003, 18KJA520010), and the Open Program of Neusoft Corporation (No. SKLSAOP1801).

Access to Document

10.1007/978-3-030-59419-0_5

Cite this

@inproceedings{df17049e57294d45ac718837f091895a,

title = "MemTimes: Temporal Scoping of Facts with Memory Network",

abstract = "This paper works on temporal scoping, i.e., adding time interval to facts in Knowledge Bases (KBs). The existing methods for temporal scope inference and extraction still suffer from low accuracy. In this paper, we propose a novel neural model based on Memory Network to do temporal reasoning among sentences for the purpose of temporal scoping. We design proper ways to encode both semantic and temporal information contained in the mention set of each fact, which enables temporal reasoning with Memory Network. We also find ways to remove the effect brought by noisy sentences, which can further improve the robustness of our approach. The experiments show that this solution is highly effective for detecting temporal scope of facts.",

author = "Siyuan Cao and Qiang Yang and Zhixu Li and Guanfeng Liu and Detian Zhang and Jiajie Xu",

note = "KAUST Repository Item: Exported on 2020-10-15 Acknowledgements: This research is partially supported by Natural Science Foundation of Jiangsu Province (No. BK20191420), National Natural Science Foundation of China (Grant No. 61632016, 61572336, 61572335, 61772356), Natural Science Research Project of Jiangsu Higher Education Institution (No. 17KJA520003, 18KJA520010), and the Open Program of Neusoft Corporation (No. SKLSAOP1801).",

year = "2020",

month = sep,

day = "21",

doi = "10.1007/978-3-030-59419-0_5",

language = "English (US)",

isbn = "9783030594183",

pages = "70--86",

booktitle = "Database Systems for Advanced Applications",

publisher = "Springer International Publishing",

}

TY - GEN

T1 - MemTimes: Temporal Scoping of Facts with Memory Network

AU - Cao, Siyuan

AU - Yang, Qiang

AU - Li, Zhixu

AU - Liu, Guanfeng

AU - Zhang, Detian

AU - Xu, Jiajie

N1 - KAUST Repository Item: Exported on 2020-10-15 Acknowledgements: This research is partially supported by Natural Science Foundation of Jiangsu Province (No. BK20191420), National Natural Science Foundation of China (Grant No. 61632016, 61572336, 61572335, 61772356), Natural Science Research Project of Jiangsu Higher Education Institution (No. 17KJA520003, 18KJA520010), and the Open Program of Neusoft Corporation (No. SKLSAOP1801).

PY - 2020/9/21

Y1 - 2020/9/21

N2 - This paper works on temporal scoping, i.e., adding time interval to facts in Knowledge Bases (KBs). The existing methods for temporal scope inference and extraction still suffer from low accuracy. In this paper, we propose a novel neural model based on Memory Network to do temporal reasoning among sentences for the purpose of temporal scoping. We design proper ways to encode both semantic and temporal information contained in the mention set of each fact, which enables temporal reasoning with Memory Network. We also find ways to remove the effect brought by noisy sentences, which can further improve the robustness of our approach. The experiments show that this solution is highly effective for detecting temporal scope of facts.

AB - This paper works on temporal scoping, i.e., adding time interval to facts in Knowledge Bases (KBs). The existing methods for temporal scope inference and extraction still suffer from low accuracy. In this paper, we propose a novel neural model based on Memory Network to do temporal reasoning among sentences for the purpose of temporal scoping. We design proper ways to encode both semantic and temporal information contained in the mention set of each fact, which enables temporal reasoning with Memory Network. We also find ways to remove the effect brought by noisy sentences, which can further improve the robustness of our approach. The experiments show that this solution is highly effective for detecting temporal scope of facts.

UR - http://hdl.handle.net/10754/665580

UR - http://link.springer.com/10.1007/978-3-030-59419-0_5

UR - http://www.scopus.com/inward/record.url?scp=85092102852&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-59419-0_5

DO - 10.1007/978-3-030-59419-0_5

M3 - Conference contribution

SN - 9783030594183

SP - 70

EP - 86

BT - Database Systems for Advanced Applications

PB - Springer International Publishing

ER -

MemTimes: Temporal Scoping of Facts with Memory Network

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this