Difference between revisions of "Eosc/norbert/benchmark"

From Nordic Language Processing Laboratory
Jump to: navigation, search
Line 1: Line 1:
 
= Emerging Thoughts on Benchmarking =
 
= Emerging Thoughts on Benchmarking =
  
This would be natural places to start:
+
The following would be natural places to start. For most of these one would need to find suitable code for existing BERT-based architectures for e.g. English. For the first though, document-level SA on NoReC, Jeremy would have an existing set-up for using mBERT.
  
*[https://github.com/ltgoslo/norec_fine NoReC]; for document-level sentiment analysis (i.e. rating prediction)
+
*[https://github.com/ltgoslo/norec_fine NoReC]; for document-level sentiment analysis (i.e. rating prediction).
 
*[https://github.com/ltgoslo/norec_fine NoReC_fine]; for fine-grained sentiment analysis (e.g. predicting target expression + polarity)
 
*[https://github.com/ltgoslo/norec_fine NoReC_fine]; for fine-grained sentiment analysis (e.g. predicting target expression + polarity)
 
*[https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-10/ NDT]; for dependency parsing or PoS tagging (perhaps best to use the UD version)
 
*[https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-10/ NDT]; for dependency parsing or PoS tagging (perhaps best to use the UD version)
 
*[https://github.com/ltgoslo/norne NorNE]; for named entity recognition, extends NDT (also available for the UD version)
 
*[https://github.com/ltgoslo/norne NorNE]; for named entity recognition, extends NDT (also available for the UD version)

Revision as of 18:06, 3 December 2020

Emerging Thoughts on Benchmarking

The following would be natural places to start. For most of these one would need to find suitable code for existing BERT-based architectures for e.g. English. For the first though, document-level SA on NoReC, Jeremy would have an existing set-up for using mBERT.

  • NoReC; for document-level sentiment analysis (i.e. rating prediction).
  • NoReC_fine; for fine-grained sentiment analysis (e.g. predicting target expression + polarity)
  • NDT; for dependency parsing or PoS tagging (perhaps best to use the UD version)
  • NorNE; for named entity recognition, extends NDT (also available for the UD version)