TY - GEN
T1 - An Argument Extraction Decoder in Open Information Extraction
AU - Li, Yucheng
AU - Yang, Yan
AU - Hu, Qinmin
AU - Chen, Chengcai
AU - He, Liang
N1 - Publisher Copyright:
© 2021, Springer Nature Switzerland AG.
PY - 2021
Y1 - 2021
N2 - In this paper, we present a feature fusion decoder for argument extraction in Open Information Extraction (Open IE), where we challenge argument extraction as a predicate-dependent task. Therefore, we create a predicate-specific embedding layer to allow the argument extraction module fully shares the predicate information and the contextualized information of the given sentence, after using a pre-trained BERT model to achieve the predicates. After that, we propose a decoder in argument extraction that leverages both token features and span features to extract arguments with two steps as argument boundary identification by token features and argument role labeling by span features. Experimental results show that the proposed decoder significantly enhances the extraction performance. Our approach establishes a new state-of-the-art result on two benchmarks as OIE2016 and Re-OIE2016.
AB - In this paper, we present a feature fusion decoder for argument extraction in Open Information Extraction (Open IE), where we challenge argument extraction as a predicate-dependent task. Therefore, we create a predicate-specific embedding layer to allow the argument extraction module fully shares the predicate information and the contextualized information of the given sentence, after using a pre-trained BERT model to achieve the predicates. After that, we propose a decoder in argument extraction that leverages both token features and span features to extract arguments with two steps as argument boundary identification by token features and argument role labeling by span features. Experimental results show that the proposed decoder significantly enhances the extraction performance. Our approach establishes a new state-of-the-art result on two benchmarks as OIE2016 and Re-OIE2016.
KW - Argument extraction
KW - Decoder
KW - Open Information Extraction
KW - Span extraction
UR - https://www.scopus.com/pages/publications/85107380611
U2 - 10.1007/978-3-030-72113-8_21
DO - 10.1007/978-3-030-72113-8_21
M3 - 会议稿件
AN - SCOPUS:85107380611
SN - 9783030721121
T3 - Lecture Notes in Computer Science
SP - 313
EP - 326
BT - Advances in Information Retrieval - 43rd European Conference on IR Research, ECIR 2021, Proceedings
A2 - Hiemstra, Djoerd
A2 - Moens, Marie-Francine
A2 - Mothe, Josiane
A2 - Perego, Raffaele
A2 - Potthast, Martin
A2 - Sebastiani, Fabrizio
PB - Springer Science and Business Media Deutschland GmbH
T2 - 43rd European Conference on Information Retrieval, ECIR 2021
Y2 - 28 March 2021 through 1 April 2021
ER -