Create a test suite to allow for comparisons with other sentiment models.
KennethEnevoldsen opened this issue · comments
Create a series of tests to apply the model to for each of the languages.
When the test suite is done test the following models:
- Only lexicon (try with AFINNs also - not lemmatized)
- Tree-based negations
- POS-based negations
intended usage:
import asent
import spacy
from asent.benchmarks import benchmark
nlp = ...
nlp.add_pipe("asen...
grid = {"valence": [...],
is_negated": [...]}
perf = benchmark(lang="da", grid)
This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.
This issue was closed because it has been stale for 5 days with no activity.