Question Answering On Qasent
評価指標
MAP
MRR
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | MAP | MRR | Paper Title | Repository |
|---|---|---|---|---|
| Attentive LSTM | 0.7339 | 0.8117 | Neural Variational Inference for Text Processing | |
| LSTM (lexical overlap + dist output) | 0.7228 | 0.7986 | Neural Variational Inference for Text Processing | |
| LSTM | 0.6436 | 0.7235 | Neural Variational Inference for Text Processing | |
| Paragraph vector | 0.5213 | 0.6023 | Distributed Representations of Sentences and Documents | |
| Bigram-CNN | 0.5693 | 0.6613 | Deep Learning for Answer Sentence Selection | |
| Bigram-CNN (lexical overlap + dist output) | 0.7113 | 0.7846 | Deep Learning for Answer Sentence Selection | |
| Paragraph vector (lexical overlap + dist output) | 0.6762 | 0.7514 | Distributed Representations of Sentences and Documents |
0 of 7 row(s) selected.