TY - GEN
T1 - Climate event detection algorithm based on climate category word embedding
AU - Wang, Hengyi
AU - Niu, Zhendong
N1 - Publisher Copyright:
© 2018 Association for Computing Machinery.
PY - 2018/4/28
Y1 - 2018/4/28
N2 - Detecting climate events efficiently and accurately is important in traffic warning, disaster warning, and disease prevention. Given that ordinary event detection algorithms are ignored in climate domain's knowledge, the results of climate domain's event detection are not satisfactory. This paper proposes a climate event detection algorithm based on climate category word embedding(CEDCWE). This method combines the climate category word embedding and typical factors of climate events as a document representation model to express detailed information of climate documents and detect climate events efficiently and accurately. Compared with other methods, the CEDCWE algorithm can generate better climate document representations and climate event detection results. In the experiments, we acquire the datasets by a web crawler and evaluate our CEDCWE on real-world climate event detection tasks. Experimental results show that our CEDCWE is effective in climate document representation and outperforms typical methods.
AB - Detecting climate events efficiently and accurately is important in traffic warning, disaster warning, and disease prevention. Given that ordinary event detection algorithms are ignored in climate domain's knowledge, the results of climate domain's event detection are not satisfactory. This paper proposes a climate event detection algorithm based on climate category word embedding(CEDCWE). This method combines the climate category word embedding and typical factors of climate events as a document representation model to express detailed information of climate documents and detect climate events efficiently and accurately. Compared with other methods, the CEDCWE algorithm can generate better climate document representations and climate event detection results. In the experiments, we acquire the datasets by a web crawler and evaluate our CEDCWE on real-world climate event detection tasks. Experimental results show that our CEDCWE is effective in climate document representation and outperforms typical methods.
KW - Category word embedding
KW - Climate domain
KW - Event detection
UR - http://www.scopus.com/inward/record.url?scp=85051529234&partnerID=8YFLogxK
U2 - 10.1145/3220199.3220203
DO - 10.1145/3220199.3220203
M3 - Conference contribution
AN - SCOPUS:85051529234
SN - 9781450364263
T3 - ACM International Conference Proceeding Series
SP - 71
EP - 77
BT - ICBDC 2018 - Proceedings of 2018 International Conference on Big Data and Computing
PB - Association for Computing Machinery
T2 - 2018 International Conference on Big Data and Computing, ICBDC 2018
Y2 - 28 April 2018 through 30 April 2018
ER -