BenchIE: a benchmark and evaluation framework for comprehensive evaluation of OIE systems for English, Chinese and German. In contrast to existing OIE benchmarks, BenchIE takes into account informational equivalence of extractions: our gold standard consists of fact synsets, clusters in which we exhaustively list all surface forms of the same fact.
Variants: BenchIE
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Open Information Extraction | CompactIE | CompactIE: Compact Facts in Open … | 2022-05-05 |
| Open Information Extraction | MinIE | BenchIE: A Framework for Multi-Faceted … | 2021-09-14 |
| Open Information Extraction | M2OIE (EN) | BenchIE: A Framework for Multi-Faceted … | 2021-09-14 |
| Open Information Extraction | ROIE-T | BenchIE: A Framework for Multi-Faceted … | 2021-09-14 |
| Open Information Extraction | OpenIE6 | BenchIE: A Framework for Multi-Faceted … | 2021-09-14 |
| Open Information Extraction | M2OIE (ZH) | BenchIE: A Framework for Multi-Faceted … | 2021-09-14 |
| Open Information Extraction | ROIE-N | BenchIE: A Framework for Multi-Faceted … | 2021-09-14 |
| Open Information Extraction | Stanford OIE | BenchIE: A Framework for Multi-Faceted … | 2021-09-14 |
| Open Information Extraction | M2OIE (DE) | BenchIE: A Framework for Multi-Faceted … | 2021-09-14 |
| Open Information Extraction | ClausIE | BenchIE: A Framework for Multi-Faceted … | 2021-09-14 |
| Open Information Extraction | Naive OIE | BenchIE: A Framework for Multi-Faceted … | 2021-09-14 |
Recent papers with results on this dataset: