Add seqeval-relaxed comparison

README.md

@@ -135,20 +135,20 @@ The output for different modes and error_formats is:
 A basic [DistilBERT model](https://huggingface.co/docs/transformers/model_doc/distilbert) downstream-trained on the 
 [WNUT-17](https://huggingface.co/datasets/wnut_17) dataset sheds the following F1 scores. Seqeval is shown for comparison.
 
-|             | Overall | Location | Group  | Person | Creative Work | Corporation | Product |
-|-------------|---------|----------|--------|--------|---------------|-------------|---------|
-| Traditional | 0.2803  | 0.4124   | 0.0412 | 0.4105 | 0.0           | 0.1985      | 0.0     |
-| Fair        | 0.3199  | 0.5247   | 0.0459 | 0.4643 | 0.0           | 0.2666      | 0.0     |
-| Weighted    | 0.3842  | 0.5638   | 0.0681 | 0.5676 | 0.0           | 0.2910      | 0.0     |
-| seqeval     | 0.2222  | 0.3425   | 0.0413 | 0.3598 | 0.0           | 0.0408      | 0.0     |
+|                 | Overall | Location | Group  | Person | Creative Work | Corporation | Product |
+|-----------------|---------|----------|--------|--------|---------------|-------------|---------|
+| Traditional     | 0.2803  | 0.4124   | 0.0412 | 0.4105 | 0.0           | 0.1985      | 0.0     |
+| Fair            | 0.3199  | 0.5247   | 0.0459 | 0.4643 | 0.0           | 0.2666      | 0.0     |
+| Weighted        | 0.3842  | 0.5638   | 0.0681 | 0.5676 | 0.0           | 0.2910      | 0.0     |
+| seqeval strict  | 0.2222  | 0.3425   | 0.0413 | 0.3598 | 0.0           | 0.0408      | 0.0     |
+| seqeval relaxed | 0.2803  | 0.4124   | 0.0412 | 0.4105 | 0.0           | 0.1985      | 0.0     |
 
 ## Limitations and Bias
 The metric is restricted to the input schemes admitted by seqeval. For example, the application does not support numerical
 label inputs (odd for Beginning, even for Inside and zero for Outside).
 
 The choice of custom weights for wheighted evaluation is subjective to the user. Neither weighted nor fair evaluations 
-can be compared to traditional span-based metrics used in other pairs of datasets-models. Although traditional mode should
-be comparable to these classical span-based metrics, there is a noticeable gap to seqeval, for instance.
+can be compared to traditional span-based metrics used in other pairs of datasets-models.
 
 ## Citation
 Ortmann, Katrin. 2022. Fine-Grained Error Analysis and Fair Evaluation of Labeled Spans. In *Proceedings of the Language Resources and Evaluation Conference (LREC)*, Marseille, France, pages 1400–1407. [PDF](https://aclanthology.org/2022.lrec-1.150.pdf)