Difference between revisions of "MUC-7 (State of the art)"
Jump to navigation
Jump to search
| Line 15: | Line 15: | ||
! System name | ! System name | ||
! Short description | ! Short description | ||
| + | ! System type | ||
! Main publications | ! Main publications | ||
! Software | ! Software | ||
! Results (F) | ! Results (F) | ||
|- | |- | ||
| − | | | + | | Annotator |
| Human annotator | | Human annotator | ||
| + | | - | ||
| [http://www.itl.nist.gov/iad/894.02/related_projects/muc/proceedings/muc_7_toc.html MUC-7 proceedings] | | [http://www.itl.nist.gov/iad/894.02/related_projects/muc/proceedings/muc_7_toc.html MUC-7 proceedings] | ||
| − | | | + | | - |
| 97.60% | | 97.60% | ||
|- | |- | ||
| LTG | | LTG | ||
| Best MUC-7 participant | | Best MUC-7 participant | ||
| + | | H | ||
| Mikheev, Grover and Moens (1998) | | Mikheev, Grover and Moens (1998) | ||
| − | | | + | | - |
| 93.39% | | 93.39% | ||
| + | |- | ||
| + | | Baseline | ||
| + | | Vocabulary transfer from training to testing | ||
| + | | S | ||
| + | | Whitelaw and Patrick (2003) | ||
| + | | - | ||
| + | | 58.89% | ||
|- | |- | ||
|} | |} | ||
| + | |||
| + | * '''System type''': R = hand-crafted rules, S = supervised learning, U = unsupervised learning, H = hybrid | ||
== References == | == References == | ||
| − | Mikheev, A., Grover, C. | + | Mikheev, A., Grover, C. and Moens, M. (1998). [http://www-nlpir.nist.gov/related_projects/muc/proceedings/muc_7_proceedings/ltg_muc7.pdf Description of the LTG system used for MUC-7]. ''Proceedings of the Seventh Message Understanding Conference (MUC-7)''. Fairfax, Virginia. |
| + | |||
| + | Whitelaw, C. and Patrick, J. (2003) [http://www.springerlink.com/content/ju66c6a2734fl20u/ Evaluating Corpora for Named Entity Recognition Using Character-Level Features]. ''Proceeding of the 16th Australian Conference on AI''. Perth, Australia. | ||
== See also == | == See also == | ||
Revision as of 13:35, 31 July 2007
- Performance measure: F = 2 * Precision * Recall / (Recall + Precision)
- Precision: percentage of named entities found by the algorithm that are correct
- Recall: percentage of named entities defined in the corpus that were found by the program
- Exact calculation of precision and recall is explained in the MUC scoring software
- Training data: Training section of MUC-7 dataset
- Testing data: Formal section of MUC-7 dataset
Table of results
| System name | Short description | System type | Main publications | Software | Results (F) |
|---|---|---|---|---|---|
| Annotator | Human annotator | - | MUC-7 proceedings | - | 97.60% |
| LTG | Best MUC-7 participant | H | Mikheev, Grover and Moens (1998) | - | 93.39% |
| Baseline | Vocabulary transfer from training to testing | S | Whitelaw and Patrick (2003) | - | 58.89% |
- System type: R = hand-crafted rules, S = supervised learning, U = unsupervised learning, H = hybrid
References
Mikheev, A., Grover, C. and Moens, M. (1998). Description of the LTG system used for MUC-7. Proceedings of the Seventh Message Understanding Conference (MUC-7). Fairfax, Virginia.
Whitelaw, C. and Patrick, J. (2003) Evaluating Corpora for Named Entity Recognition Using Character-Level Features. Proceeding of the 16th Australian Conference on AI. Perth, Australia.