Language Modelling on Mathematical expression EVAL (test)
100Exact MatchLSTM
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LSTMEncoding Setup=memory injection2026.01 | 100 | 100 | |
| SiamEncoding Setup=memory injection2026.01 | 100 | 100 | |
| BERT-GraphSAGE (+ addition QKV)Backbone=BERT-GraphSAGE, Injection Method=addition, Injection Target=QKV2026.01 | 100 | 100 | |
| BERT-GraphSAGE (+ fusion QKV)Backbone=BERT-GraphSAGE, Injection Method=fusion, Injection Target=QKV2026.01 | 100 | 100 | |
| BERT-TransCONV (+ addition QKV)Backbone=BERT-TransCONV, Injection Method=addition, Injection Target=QKV2026.01 | 100 | 100 | |
| Optimus(768)Latent Size=7682026.01 | 99 | 99 | |
| BERT-GraphSAGE (+ addition Q)Backbone=BERT-GraphSAGE, Injection Method=addition, Injection Target=Q2026.01 | 99 | 99 | |
| BERT-TransCONV (+ fusion QKV)Backbone=BERT-TransCONV, Injection Method=fusion, Injection Target=QKV2026.01 | 99 | 99 | |
| VGAEEncoding Setup=memory injection2026.01 | 98 | 99 | |
| BERT-TransCONV (+ addition Q)Backbone=BERT-TransCONV, Injection Method=addition, Injection Target=Q2026.01 | 98 | 99 | |
| BERT-TransCONV (+ fusion Q)Backbone=BERT-TransCONV, Injection Method=fusion, Injection Target=Q2026.01 | 96 | 98 | |
| BERT-GraphSAGE (+ fusion Q)Backbone=BERT-GraphSAGE, Injection Method=fusion, Injection Target=Q2026.01 | 94 | 97 | |
| Optimus (GraphEncoder + TransCONV)Backbone=GraphEncoder2026.01 | 89 | 95 | |
| Optimus (GraphEncoder + GraphSAGE)Backbone=GraphEncoder2026.01 | 88 | 96 | |
| AAE(768)Latent Size=7682026.01 | 10 | 75 | |
| LAAE(768)Latent Size=7682026.01 | 0 | 43 | |
| DAAE(768)Latent Size=7682026.01 | 0 | 24 | |
| β-VAE(768)Latent Size=7682026.01 | 0 | 14 | |
| Optimus (GraphEncoder + GCN)Backbone=GraphEncoder2026.01 | 0 | 40 |