Nature has inspired various ground-breaking technological developments in applications ranging from robotics to aerospace engineering and the manufacturing of medical devices. However, accessing the information captured in scientific biology texts is a time-consuming and hard task that requires domain-specific knowledge. Improving access for outsiders can help interdisciplinary research like Nature Inspired Engineering. This paper describes a dataset of 1,500 manually-annotated sentences that express domain-independent relations between central concepts in a scientific biology text, such as trade-offs and correlations. The arguments of these relations can be Multi Word Expressions and have been annotated with modifying phrases to form non-projective graphs. The dataset allows for training and evaluating Relation Extraction algorithms that aim for coarse-grained typing of scientific biological documents, enabling a high-level filter for engineers.
%0 Journal Article
%1 kruiper_scientific_2020
%A Kruiper, Ruben
%A Vincent, Julian F. V.
%A Chen-Burger, Jessica
%A Desmulliez, Marc P. Y.
%A Konstas, Ioannis
%D 2020
%J arXiv:2005.07753 cs
%K korpora terminologieextraktion
%T A scientific information extraction dataset for nature inspired engineering
%U http://arxiv.org/abs/2005.07753
%X Nature has inspired various ground-breaking technological developments in applications ranging from robotics to aerospace engineering and the manufacturing of medical devices. However, accessing the information captured in scientific biology texts is a time-consuming and hard task that requires domain-specific knowledge. Improving access for outsiders can help interdisciplinary research like Nature Inspired Engineering. This paper describes a dataset of 1,500 manually-annotated sentences that express domain-independent relations between central concepts in a scientific biology text, such as trade-offs and correlations. The arguments of these relations can be Multi Word Expressions and have been annotated with modifying phrases to form non-projective graphs. The dataset allows for training and evaluating Relation Extraction algorithms that aim for coarse-grained typing of scientific biological documents, enabling a high-level filter for engineers.
@article{kruiper_scientific_2020,
abstract = {Nature has inspired various ground-breaking technological developments in applications ranging from robotics to aerospace engineering and the manufacturing of medical devices. However, accessing the information captured in scientific biology texts is a time-consuming and hard task that requires domain-specific knowledge. Improving access for outsiders can help interdisciplinary research like Nature Inspired Engineering. This paper describes a dataset of 1,500 manually-annotated sentences that express domain-independent relations between central concepts in a scientific biology text, such as trade-offs and correlations. The arguments of these relations can be Multi Word Expressions and have been annotated with modifying phrases to form non-projective graphs. The dataset allows for training and evaluating Relation Extraction algorithms that aim for coarse-grained typing of scientific biological documents, enabling a high-level filter for engineers.},
added-at = {2020-05-24T19:29:18.000+0200},
author = {Kruiper, Ruben and Vincent, Julian F. V. and Chen-Burger, Jessica and Desmulliez, Marc P. Y. and Konstas, Ioannis},
biburl = {https://www.bibsonomy.org/bibtex/2c5ae9b42900f9eaa1d747bb331f11f6f/lepsky},
interhash = {328563d3b6213007ca82e89c523cc14a},
intrahash = {c5ae9b42900f9eaa1d747bb331f11f6f},
journal = {arXiv:2005.07753 [cs]},
keywords = {korpora terminologieextraktion},
month = may,
note = {arXiv: 2005.07753},
timestamp = {2020-06-20T12:28:08.000+0200},
title = {A scientific information extraction dataset for nature inspired engineering},
url = {http://arxiv.org/abs/2005.07753},
urldate = {2020-05-24},
year = 2020
}