Conference item icon

Conference item

Systematic comparison of neural architectures and training approaches for open information extraction

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 ...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publication website:
https://www.aclweb.org/anthology/2020.emnlp-main.690.pdf

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
ORCID:
0000-0002-7644-1668
Publisher:
Association for Computational Linguistics
Pages:
8554-8565
Publication date:
2020-11-16
Acceptance date:
2020-09-15
Event title:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)
Event location:
Online
Event website:
https://2020.emnlp.org/
Event start date:
2020-11-16
Event end date:
2020-11-20
Language:
English
Keywords:
Pubs id:
1145286
Local pid:
pubs:1145286
Deposit date:
2020-11-13

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP