Systematic Comparison of Neural Architectures and Training Approaches for Open Information Extraction

Patrick Hohenecker, Frank Mtumbuka, Vid Kocijan, Thomas Lukasiewicz


Abstract
The goal of open information extraction (OIE) is to extract facts from natural language text, and to represent them as structured triples of the form <subject,predicate, object>. For example, given the sentence “Beethoven composed the Ode to Joy.”, we are expected to extract the triple <Beethoven, composed, Ode to Joy>. In this work, we systematically compare different neural network architectures and training approaches, and improve the performance of the currently best models on the OIE16 benchmark (Stanovsky and Dagan, 2016) by 0.421 F1 score and 0.420 AUC-PR, respectively, in our experiments (i.e., by more than 200% in both cases). Furthermore, we show that appropriate problem and loss formulations often affect the performance more than the network architecture.
Anthology ID:
2020.emnlp-main.690
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8554–8565
Language:
URL:
https://aclanthology.org/2020.emnlp-main.690
DOI:
10.18653/v1/2020.emnlp-main.690
Bibkey:
Cite (ACL):
Patrick Hohenecker, Frank Mtumbuka, Vid Kocijan, and Thomas Lukasiewicz. 2020. Systematic Comparison of Neural Architectures and Training Approaches for Open Information Extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8554–8565, Online. Association for Computational Linguistics.
Cite (Informal):
Systematic Comparison of Neural Architectures and Training Approaches for Open Information Extraction (Hohenecker et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.690.pdf
Video:
 https://slideslive.com/38938963