Table 6.

Overall performance of all runs in Task 1—Named entity recognition.

Run	Exact-match			Relaxed-match
	P	R	F	P	R	F
Melaxtech-run1	0.9571	0.9570	0.9570	0.9690	0.9687	0.9688
Melaxtech-run2	0.9587	0.9529	0.9558	0.9697	0.9637	0.9667
Melaxtech-run3	0.9572	0.9510	0.9541	0.9688	0.9624	0.9656
VinAI-run2*	0.9538	0.9504	0.9521	0.9737	0.9716	0.9726
VinAI-run1	0.9462	0.9405	0.9433	0.9707	0.9661	0.9684
Lasige_BioTM-run1	0.9327	0.9457	0.9392	0.9590	0.9671	0.9630
BiTeM-run3	0.9378	0.9087	0.9230	0.9692	0.9558	0.9624
BiTeM-run2	0.9083	0.9114	0.9098	0.9510	0.9684	0.9596
NextMove/Minesoft-run1	0.9042	0.8924	0.8983	0.9301	0.9181	0.9240
NextMove/Minesoft-run2	0.9037	0.8918	0.8977	0.9294	0.9178	0.9236
Baseline	0.9071	0.8723	0.8893	0.9219	0.8893	0.9053
NLP@VCU-run1	0.8747	0.8570	0.8658	0.9524	0.9513	0.9518
KFU_NLP-run1	0.8930	0.8386	0.8649	0.9701	0.9255	0.9473
NLP@VCU-run2	0.8705	0.8502	0.8602	0.9490	0.9446	0.9468
NLP@VCU-run3	0.8665	0.8514	0.8589	0.9486	0.9528	0.9507
KFU_NLP-run2	0.8579	0.8329	0.8452	0.9690	0.9395	0.9540
NextMove/Minesoft-run3	0.8281	0.8083	0.8181	0.8543	0.8350	0.8445
KFU_NLP-run3	0.8197	0.8027	0.8111	0.9579	0.9350	0.9463
BiTeM-run1	0.8330	0.7799	0.8056	0.8882	0.8492	0.8683
OntoChem-run1	0.7927	0.5983	0.6819	0.8441	0.6364	0.7257
AUKBC-run1	0.6763	0.4074	0.5085	0.8793	0.5334	0.6640
AUKBC-run2	0.4895	0.1913	0.2751	0.6686	0.2619	0.3764
SSN_NLP-run1	0.2923	0.1911	0.2311	0.8633	0.4930	0.6276
SSN_NLP-run2	0.2908	0.1911	0.2307	0.8595	0.4932	0.6267
JU_INDIA-run1	0.1411	0.0824	0.1041	0.2522	0.1470	0.1857
JU_INDIA-run2	0.0322	0.0151	0.0206	0.1513	0.0710	0.0966
JU_INDIA-run3	0.0322	0.0151	0.0206	0.1513	0.0710	0.0966

Here, P, R, and F represents the Precision, Recall, and F₁-score, respectively. For each metric, we highlight the best result in bold and the second best result in italic. The results are ordered by their performance in terms of F₁-score under exact-match.

^*This run was received after evaluation phase and thus was not included in official results.