41 to 50 of 55 Results
Aug 19, 2019
Kotnis, Bhushan, 2019, "KGE Algorithms", https://doi.org/10.11588/data/CSXYSS, heiDATA, V1
An updated method for link prediction that uses a regularization factor that models relation argument types Abstract (Kotnis and Nastase, 2017): Learning relations based on evidence from knowledge repositories relies on processing the available relation instances. Knowledge repos... |
Aug 19, 2019 -
KGE Algorithms
ZIP Archive - 19.4 KB -
MD5: d2e8ac74e3f20d2cdec2225962c7e2f0
|
Jul 15, 2019
Nastase, Vivi; Kotnis, Bhushan, 2019, "Abstract graphs, abstract paths, grounded paths for Freebase and NELL", https://doi.org/10.11588/data/AVLFPZ, heiDATA, V1
We describe a method for representing knowledge graphs that capture an intensional representation of the original extensional information. This representation is very compact, and it abstracts away from individual links, allowing us to find better path candidates, as shown by the... |
Gzip Archive - 2.5 GB -
MD5: dc2a64fb2d88cccf5e62d9400cbca1af
|
Gzip Archive - 204.7 MB -
MD5: 6dfafe4e7d5b29a882b59f43ec9eb4ae
|
Plain Text - 2.7 KB -
MD5: 4c073cf79f74569a44e3687f97b0be91
|
Jul 15, 2019
Nastase, Vivi; Hitschler, Julian, 2019, "ACL word segmentation correction", https://doi.org/10.11588/data/VK99LU, heiDATA, V1
The data in this collection consists of two parallel directories, one ("raw") containing the raw text of 18850 articles from the ACL 2013/02 collection, the other ("re-segmented") the word-resegmented version of these articles, obtained using nematus, a seq2seq neural model used... |
Jul 15, 2019 -
ACL word segmentation correction
Gzip Archive - 371.1 MB -
MD5: 96d089771cde56bb9ac5296189fb403b
text files |
Jul 15, 2019 -
ACL word segmentation correction
Plain Text - 782 B -
MD5: b305fd3ce016837f601aa137fd8ecf63
|
Jul 15, 2019
Nastase, Vivi; Fritz, Devon; Frank, Anette, 2019, "DeModify", https://doi.org/10.11588/data/KIWEMF, heiDATA, V1
deModify consists of 3631 instances, each with three annotations obtained through CrowdFlower. An instance is a short story in which a modifier is annotated with respect to its impact on the information in the story, assessed through its deletion from the context: crucial, not-cr... |