1 a 9 de 9 Resultados
17 feb. 2022 -
Reproducible experiments on word and sentence similarity measures for the biomedical domain
Archivo Gzip - 3,8 MB -
MD5: cf57dfaf65f152043ff1f801da15ce75
This file contains the raw output files of a complete execution of the software clients
HESMLSTSImpactPreprocessingclient and HESMLSTSclient. |
17 feb. 2022 -
Reproducible experiments on word and sentence similarity measures for the biomedical domain
Archivo ZIP - 65,8 MB -
MD5: 903d58ac1442816cfe8ea134741dbfe2
This file contains the Java and Python code for executing the experiments detailed in this dataset and develop in HESML V2R1. IMPORTANT NOTE!. If main link fails you can download this file from https://doi.org/10.21950/hesml_v2r1_githubRelease.zip |
8 nov. 2021 -
Reproducible experiments on word and sentence similarity measures for the biomedical domain
Archivo Gzip - 20,2 GB -
MD5: 25f14da7080c2ee1b84713300d286c46
This file contains all the BERT models and dependencies evaluated in HESML V2R1 as detailed in [1]. IMPORTANT NOTE!. If main link fails you can download this file from https://doi.org/10.21950/BERTExperiments.tar.gz |
8 nov. 2021 -
Reproducible experiments on word and sentence similarity measures for the biomedical domain
Archivo ZIP - 42,8 GB -
MD5: 6c8d651f74559f16cac879722b46bff8
This file contains the BioC XML files in unicode format from PMC Corpus The dataset has been downloaded from 1 on 5 June, 2019. IMPORTANT NOTE!. If main link fails you can download this file from https://doi.org/10.21950/BioCManuscriptCorpus.zip |
8 nov. 2021 -
Reproducible experiments on word and sentence similarity measures for the biomedical domain
Archivo Gzip - 19,4 GB -
MD5: a27819702fb003f346d7ec541533a480
This file contains all the character and sentence pretrained models evaluated in HESML V2R1 as detailed in [1]. IMPORTANT NOTE!. If main link fails you can download this file from https://doi.org/10.21950/CharacterAndSentenceEmbeddings.tar.gz |
8 nov. 2021 -
Reproducible experiments on word and sentence similarity measures for the biomedical domain
Archivo ZIP - 100,9 GB -
MD5: 079326772685a95c86e0ed003137bd42
IMPORTANT NOTE!. If main link fails you can download this file from https://doi.org/10.21950/PreprocessedBioCCorpus.zip |
8 nov. 2021 -
Reproducible experiments on word and sentence similarity measures for the biomedical domain
Archivo Gzip - 39,0 GB -
MD5: 6ccf1d8b29b824cafd36ac1d3a238d1b
This file contains the Word Embedding pretrained models detailed in HESML V2R1 [1] and our pretrained model based on Fastext [3] in the BioC PMC Corpus [4].
Our pretrained model has been trained on Fastext skipgram model using the parameters from [1] in the BioC PMC Corpus [4].... |
3 jun. 2021 -
Formal concept analysis for topic detection: a clustering quality experimental analysis
Archivo Gzip - 2,7 MB -
MD5: c79dfaaeba4970321576a7ce1650b40f
|
30 abr. 2021 -
HESML V1R5 Java software library of ontology-based semantic similarity measures and information content models
Archivo ZIP - 143,3 MB -
MD5: 732ab8e8edd746b4705714fd638253bf
|