Research Article
Few-Shot Relation Extraction via the Entity Feature Enhancement and Attention-Based Prototypical Network
Table 2
Number and proportion of text length (in terms of number of characters) intervals in the three datasets.
| Datasets | Length | 0–20 | 20–30 | 30–40 | 40–60 | 60–80 | >80 |
| Bridge-FewRel | Num. | 7926 | 3850 | 2195 | 4280 | 142 | 57 | Prop. | 43% | 21% | 12% | 23% | 0.8% | 0.2% |
| TinyRel-CM | Num. | 28 | 93 | 174 | 348 | 290 | 424 | Prop. | 2% | 7% | 12.8% | 25.6% | 21% | 31.6% |
| FewRel 1.0 | Num. | 14905 | 27857 | 13238 | 0 | 0 | 0 | Prop. | 27% | 50% | 23% | 0% | 0% | 0% |
|
|