Eosc/norbert/benchmark

Emerging Thoughts on Benchmarking

The following would be natural places to start. For most of these, while we do have baseline numbers to compare to, we do not have existing set-ups where we could simply plug in a Norwegian BERT and rund, so we may need to identify suitable code for existing BERT-based architectures for e.g. English to re-use. For the first task though (document-level SA on NoReC) Jeremy would have an existing set-up for using mBERT that we could perhaps use.

NLP tasks

NoReC*

• NoReC_fine: structured sentiment analysis
• NoReC_sentences sentence-level 2/3-way polarity
• NoReC_neg: negation cues and scopes (evaluation is still being developed)

Linguistic pipeline (dependency parsing or PoS tagging)

• Bokmaal
• Nynorsk
• Spoken dialects

Lexical

• Word sense disambiguation in context
• Norwegian synonyms (for static models)
• Norwegian analogies (for static models)
• NorSentLex: Sentiment lexicon

Text classification

• NoReC; document-level ratings.
• Talk of Norway
• NorDial