Individual results

View docs

View in-depth performance of a single language model on a single test suite.

Region-by-region surprisal
Sample item for Negative Polarity Licensing (any; with subject relative clause)
Item
Condition
Licensor np compl rc_verb rc_dp rc_obj matrix_v npi continuation
Item Condition Licensor np compl rc_verb rc_dp rc_obj matrix_v npi continuation
1 neg_pos No author that liked the senators has had any success
1 neg_neg No author that liked no senators has had any success
1 pos_pos The author that liked the senators has had any success
1 pos_neg The author that liked no senators has had any success
Prediction performance for Transformer XL on Negative Polarity Licensing (any; with subject relative clause)
Accuracy
Formula
Description
AccuracyPredictionDescription
100.00% (583,neg_pos/8,npi) < (581,pos_pos/8,npi) No description provided.
86.84% (582,neg_neg/8,npi) < (584,pos_neg/8,npi) No description provided.
15.79% (583,neg_pos/8,npi) < (584,pos_neg/8,npi) No description provided.