@inproceedings{lek-etal-2020-provenance,
title = "Provenance for Linguistic Corpora through Nanopublications",
author = "Lek, Timo and
de Groot, Anna and
Kuhn, Tobias and
Morante, Roser",
booktitle = "Proceedings of the 14th Linguistic Annotation Workshop",
month = dec,
year = "2020",
address = "Barcelona, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.law-1.2",
pages = "13--23",
abstract = "Research in Computational Linguistics is dependent on text corpora for training and testing new tools and methodologies. While there exists a plethora of annotated linguistic information, these corpora are often not interoperable without significant manual work. Moreover, these annota-tions might have evolved into different versions, making it challenging for researchers to know the data{'}s provenance. This paper addresses this issue with a case study on event annotated corpora and by creating a new, more interoperable representation of this data in the form of nanopublications. We demonstrate how linguistic annotations from separate corpora can be reliably linked from the start, and thereby be accessed and queried as if they were a single dataset. We describe how such nanopublications can be created and demonstrate how SPARQL queries can be performed to extract interesting content from the new representations. The queries show that information of multiple corpora can be retrieved more easily and effectively because the information of different corpora is represented in a uniform data format.",
}
Markdown (Informal)
[Provenance for Linguistic Corpora through Nanopublications](https://aclanthology.org/2020.law-1.2) (Lek et al., LAW 2020)
ACL