11 to 20 of 184 Results
ZIP Archive - 46.4 KB -
MD5: 727dde9bcf6285b968ebbccc5459674b
|
Nov 13, 2023 -
Neural PP Attachment Disambiguation Systems
ZIP Archive - 53.0 KB -
MD5: 134dd6ae443bab1531d6cab22d88b54a
|
Nov 13, 2023 -
Head Selection Parsers and LSTM Labelers
ZIP Archive - 58.8 KB -
MD5: 1994899f6e96118e147ea9565193198b
|
ZIP Archive - 1.6 MB -
MD5: f928beb9f56c4a3e011941904872a4eb
|
Mar 26, 2020 -
Converter for content-to-head style syntactic dependencies
ZIP Archive - 10.1 MB -
MD5: 30167cb475d743ced8aa63e6349a99ce
|
Mar 26, 2020
Rehbein, Ines; Steen, Julius; Do, Bich-Ngoc; Frank, Anette, 2020, "Converter for content-to-head style syntactic dependencies", https://doi.org/10.11588/data/HE3BAZ, heiDATA, V1
A set of Python scripts that convert function-head style encodings in dependency treebanks in a content-head style encoding (as used in the UD treebanks) and vice versa (for adpositions, copula and coordination). For more information, see (Rehbein, Steen, Do & Frank 2017). |
Oct 22, 2019
Becker, Maria, 2019, "COREC – A neural multi-label COmmonsense RElation Classification system", https://doi.org/10.11588/data/E5EHBV, heiDATA, V1
We examine the learnability of Commonsense knowledge relations as represented in CONCEPTNET. We develop a neural open world multi-label classification system that focuses on the evaluation of classification accuracy for individual relations. Based on an in-depth study of the spec... |
ZIP Archive - 6.2 KB -
MD5: 04927f554601f39dd7e2d86a5e62d681
|
Nov 13, 2023 -
Neural Rerankers for Dependency Parsing
Gzip Archive - 64.5 MB -
MD5: c9066cb993f7f932b4dd3b2f57ab0df8
|
Nov 13, 2023 -
Neural Rerankers for Dependency Parsing
Gzip Archive - 58.0 MB -
MD5: 271f2b6ad94a1b3a5b5c37db948d0b7d
|