Open Information Extraction
In natural language processing, open information extraction is the task of generating a structured, machine-readable representation of the information in text, usually in the form of triples or n-ary propositions (Source: Wikipedia).
Papers
Showing 1–10 of 207 papers
All datasetsCaRBWiRe57OIE2016BenchIELSOIE-wikiLSOIENYTPenn TreebankWebDocOIE-healthcareDocOIE-transportationCaRB OIE benchmark (Greek Use-case)
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | MacroIE | F1 | 54.8 | — | Unverified |
| 2 | OpenIE 6 (CIGL-OIE) | F1 | 54 | — | Unverified |
| 3 | IMoJIE | F1 | 53.5 | — | Unverified |
| 4 | IMoJIE | F1 | 53.3 | — | Unverified |
| 5 | OpenIE6 | F1 | 52.7 | — | Unverified |
| 6 | OpenIE 6 | F1 | 52.7 | — | Unverified |
| 7 | Multi2OIE | F1 | 52.3 | — | Unverified |
| 8 | GPT-3.5-Turbo w/ Selected Demo & Uncertainty | F1 | 52.1 | — | Unverified |
| 9 | OpenIE4 | F1 | 51.6 | — | Unverified |
| 10 | LLaMA-2-70B w/ Selected Demo & Uncertainty | F1 | 51.5 | — | Unverified |