Temporally anchored spatial knowledge: Corpora and experiments

Content Provider	Scilit
Author	Vempala, Alakananda Blanco, Eduardo
Copyright Year	2020
Description	This article presents a two-step methodology to annotate temporally anchored spatial knowledge on top of OntoNotes. We first generate potential knowledge using semantic roles or syntactic dependencies and then crowdsource annotations to validate the potential knowledge. The resulting annotations indicate how long entities are or are not located somewhere and temporally anchor this spatial information. We present an in-depth corpus analysis comparing the spatial knowledge generated by manipulating roles or dependencies. Experiments show that working with syntactic dependencies instead of semantic roles allows us to generate more potential entity-related spatial knowledge and obtain better results in a realistic scenario, that is, with predicted linguistic information.
Related Links	https://www.cambridge.org/core/services/aop-cambridge-core/content/view/A4FFCFBE11875E37659D24F30E7991AF/S1351324920000212a.pdf/div-class-title-temporally-anchored-spatial-knowledge-corpora-and-experiments-div.pdf
Ending Page	543
Page Count	25
Starting Page	519
ISSN	13513249
e-ISSN	14698110
DOI	10.1017/s1351324920000212
Journal	Natural Language Engineering
Issue Number	5
Volume Number	27
Language	English
Publisher	Cambridge University Press (CUP)
Publisher Date	2020-05-20
Access Restriction	Open
Subject Keyword	Natural Language Engineering Spatial Knowledge Information Extraction
Content Type	Text
Resource Type	Article
Subject	Artificial Intelligence Linguistics and Language Software