Codesota · Models · BERT + AoAHIT & iFLYTEK1 results · 1 benchmarks
Model card

BERT + AoA.

HIT & iFLYTEKopen-source

Attention-over-Attention on BERT (Mar 2019).

§ 01 · Benchmarks

Every benchmark BERT + AoA has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01SQuAD v2.0Natural Language Processing · Question Answeringf188.6%#14/222019-03-01source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where BERT + AoA actually performs.

Natural Language Processing
1
benchmark
avg rank #14.0
§ 04 · Related models

Other HIT & iFLYTEK models scored on Codesota.

BERT + DAE + AoA (single model)
0 results
§ 05 · Sources & freshness

Where these numbers come from.

squad-shadow-page
1
result
1 of 1 rows marked verified.