| # NER Benchmark Results |
| **Model:** Minibase-NER-Small |
| **Dataset:** ner_benchmark_dataset.jsonl |
| **Sample Size:** 100 |
| **Date:** 2025-10-07T13:20:42.785262 |
|
|
| ## Overall Performance |
|
|
| | Metric | Score | Description | |
| |--------|-------|-------------| |
| | F1 Score | 0.435 | Overall NER performance (harmonic mean of precision and recall) | |
| | Precision | 0.630 | Accuracy of entity predictions | |
| | Recall | 0.343 | Ability to find all entities | |
| | Average Latency | 76.6ms | Response time performance | |
|
|
| ## Entity Type Performance |
|
|
| | Entity Type | Accuracy | Correct/Total | |
| |-------------|----------|---------------| |
| | ENTITY | 0.936 | 103/110 | |
|
|
| ## Key Improvements |
|
|
| - **BIO Tagging**: Model outputs entities in BIO (Beginning-Inside-Outside) format |
| - **Multiple Entity Types**: Supports PERSON, ORG, LOC, and MISC entities |
| - **Entity-Level Evaluation**: Metrics calculated at entity level rather than token level |
| - **Comprehensive Coverage**: Evaluates across different text domains |
|
|
| ## Example Results |
|
|
| ### Example 1 |
| **Input:** John Smith works at Google in New York and uses Python programming language.... |
| **Predicted:** PERGON, ORG... |
| **F1 Score:** 0.000 |
|
|
| ### Example 2 |
| **Input:** Microsoft Corporation announced that Satya Nadella will visit London next week.... |
| **Predicted:** 1. Microsoft Corporation... |
| **F1 Score:** 0.500 |
|
|
| ### Example 3 |
| **Input:** The University of Cambridge is located in the United Kingdom and was founded by King Henry III.... |
| **Predicted:** 1. The University of Cambridge |
| 2. King Henry III... |
| **F1 Score:** 0.800 |
|
|
|
|
