--- language: - en license: cc-by-4.0 library_name: span-marker tags: - span-marker - token-classification - ner - named-entity-recognition - generated_from_span_marker_trainer datasets: - EMBO/SourceData metrics: - precision - recall - f1 widget: - text: Comparison of ENCC-derived neurospheres treated with intestinal extract from hypoganglionosis rats, hypoganglionosis treated with Fecal microbiota transplantation (FMT) sham rat. Comparison of neuronal markers. (J) Immunofluorescence stain number of PGP9.5+. Nuclei were stained blue with DAPI; Triangles indicate PGP9.5+. - text: 'Histochemical (H & E) immunostaining (red) show T (CD3+) neutrophil (Ly6b+) infiltration in skin of mice in (A). Scale bar, 100 μm. (of CD3 Ly6b immunostaining from CsA treated mice represent seperate analyses performed on serial thin sections.) of epidermal thickness, T (CD3+) neutrophil (Ly6b+) infiltration (red) in skin thin sections from (C), (n = 6). Data information: Data represent mean ± SD. * P < 0.05, * * P < 0.01 by two -Mann-Whitney; two independent experiments.' - text: 'C African green monkey kidney epithelial (Vero) were transfected with NC, siMLKL, or miR-324-5p for 48 h. qPCR for expression of MLKL. Data information: data are represented as means ± SD of three biological replicates. Statistical analyses were performed using unpaired Student '' s t -. experiments were performed at least three times, representative data are shown.' - text: (F) Binding between FTCD p47 between p47 p97 is necessary for mitochondria aggregation mediated by FTCDwt-HA-MAO. HeLa Tet-off inducibly expressing FTCDwt-HA-MAO were transfected with mammalian expression constructs of siRNA-insensitive Flag-tagged p47wt / mutants at same time as treatment of p47 siRNA, cultured for 24 hrs. were further cultured in DOX-free medium for 48 hrs for induction of FTCD-HA-MAO. After fixation, were visualized with a monoclonal antibody to mitochondria polyclonal antibodies to HA Flag. Panels a-l display representative. Scale bar = 10 μm. (G) Binding between FTCD p97 is necessary for mitochondria aggregation mediated by FTCDwt-HA-MAO. HeLa Tet-off inducibly expressing FTCDwt-HA-MAO were transfected with mammalian expression construct of siRNA-insensitive Flag-tagged p97wt / mutant at same time as treatment with p97 siRNA. following procedures were same as in (F). Panels a-i display representative. Scale bar = 10 μm. (H) results of of (F) (G). Results are shown as mean ± SD of five sets of independent experiments, with 100 counted in each group in each independent experiment. Asterisks indicate a significant difference at P < 0.01 compared with siRNA treatment alone ('none') compared with mutant expression (Bonferroni method). - text: (b) Parkin is recruited selectively to depolarized mitochondria directs mitophagy. HeLa transfected with HA-Parkin were treated with CCCP for indicated times. Mitochondria were stained by anti-TOM20 (pseudo coloured; blue) a ΔΨm dependent MitoTracker (red). Parkin was stained with anti-HA (green). Without treatment, mitochondria are intact stained by both mitochondrial markers, whereas Parkin is equally distributed in cytoplasm. After 2 h of CCCP treatment, mitochondria are depolarized as shown by loss of MitoTracker. Parkin completely translocates to mitochondria clustering at perinuclear regions. After 24h of CCCP treatment, massive loss of mitochondria is observed as shown by disappearance of mitochondrial marker. Only Parkin-positive show mitochondrial clustering clearance, in contrast to adjacent untransfected. Scale bars, 10 μm. pipeline_tag: token-classification base_model: bert-base-uncased model-index: - name: SpanMarker with bert-base-uncased on SourceData results: - task: type: token-classification name: Named Entity Recognition dataset: name: SourceData type: EMBO/SourceData split: test metrics: - type: f1 value: 0.8336481983993405 name: F1 - type: precision value: 0.8345368269032392 name: Precision - type: recall value: 0.8327614603348888 name: Recall --- # SpanMarker with bert-base-uncased on SourceData This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model trained on the [SourceData](https://huggingface.co/datasets/EMBO/SourceData) dataset that can be used for Named Entity Recognition. This SpanMarker model uses [bert-base-uncased](https://huggingface.co/bert-base-uncased) as the underlying encoder. ## Model Details ### Model Description - **Model Type:** SpanMarker - **Encoder:** [bert-base-uncased](https://huggingface.co/bert-base-uncased) - **Maximum Sequence Length:** 256 tokens - **Maximum Entity Length:** 8 words - **Training Dataset:** [SourceData](https://huggingface.co/datasets/EMBO/SourceData) - **Language:** en - **License:** cc-by-4.0 ### Model Sources - **Repository:** [SpanMarker on GitHub](https://github.com/tomaarsen/SpanMarkerNER) - **Thesis:** [SpanMarker For Named Entity Recognition](https://raw.githubusercontent.com/tomaarsen/SpanMarkerNER/main/thesis.pdf) ### Model Labels | Label | Examples | |:---------------|:--------------------------------------------------------| | CELL_LINE | "293T", "WM266.4 451Lu", "501mel" | | CELL_TYPE | "BMDMs", "protoplasts", "epithelial" | | DISEASE | "melanoma", "lung metastasis", "breast prostate cancer" | | EXP_ASSAY | "interactions", "Yeast two-hybrid", "BiFC" | | GENEPROD | "CPL1", "FREE1 CPL1", "FREE1" | | ORGANISM | "Arabidopsis", "yeast", "seedlings" | | SMALL_MOLECULE | "polyacrylamide", "CHX", "SDS polyacrylamide" | | SUBCELLULAR | "proteasome", "D-bodies", "plasma" | | TISSUE | "Colon", "roots", "serum" | ## Evaluation ### Metrics | Label | Precision | Recall | F1 | |:---------------|:----------|:-------|:-------| | **all** | 0.8345 | 0.8328 | 0.8336 | | CELL_LINE | 0.9060 | 0.8866 | 0.8962 | | CELL_TYPE | 0.7365 | 0.7746 | 0.7551 | | DISEASE | 0.6204 | 0.6531 | 0.6363 | | EXP_ASSAY | 0.7224 | 0.7096 | 0.7160 | | GENEPROD | 0.8944 | 0.8960 | 0.8952 | | ORGANISM | 0.8752 | 0.8902 | 0.8826 | | SMALL_MOLECULE | 0.8304 | 0.8223 | 0.8263 | | SUBCELLULAR | 0.7859 | 0.7699 | 0.7778 | | TISSUE | 0.8134 | 0.8056 | 0.8094 | ## Uses ### Direct Use for Inference ```python from span_marker import SpanMarkerModel # Download from the 🤗 Hub model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-base-uncased-sourcedata") # Run inference entities = model.predict("Comparison of ENCC-derived neurospheres treated with intestinal extract from hypoganglionosis rats, hypoganglionosis treated with Fecal microbiota transplantation (FMT) sham rat. Comparison of neuronal markers. (J) Immunofluorescence stain number of PGP9.5+. Nuclei were stained blue with DAPI; Triangles indicate PGP9.5+.") ``` ### Downstream Use You can finetune this model on your own dataset.
Click to expand ```python from span_marker import SpanMarkerModel, Trainer # Download from the 🤗 Hub model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-base-uncased-sourcedata") # Specify a Dataset with "tokens" and "ner_tag" columns dataset = load_dataset("conll2003") # For example CoNLL2003 # Initialize a Trainer using the pretrained model & dataset trainer = Trainer( model=model, train_dataset=dataset["train"], eval_dataset=dataset["validation"], ) trainer.train() trainer.save_model("tomaarsen/span-marker-bert-base-uncased-sourcedata-finetuned") ```
## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:----------------------|:----|:--------|:-----| | Sentence length | 4 | 71.0253 | 2609 | | Entities per sentence | 0 | 8.3186 | 162 | ### Training Hyperparameters - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 3 ### Training Results | Epoch | Step | Validation Loss | Validation Precision | Validation Recall | Validation F1 | Validation Accuracy | |:------:|:-----:|:---------------:|:--------------------:|:-----------------:|:-------------:|:-------------------:| | 0.5237 | 3000 | 0.0162 | 0.7972 | 0.8162 | 0.8065 | 0.9520 | | 1.0473 | 6000 | 0.0155 | 0.8188 | 0.8251 | 0.8219 | 0.9560 | | 1.5710 | 9000 | 0.0155 | 0.8213 | 0.8324 | 0.8268 | 0.9563 | | 2.0946 | 12000 | 0.0163 | 0.8315 | 0.8347 | 0.8331 | 0.9581 | | 2.6183 | 15000 | 0.0167 | 0.8303 | 0.8378 | 0.8340 | 0.9582 | ### Framework Versions - Python: 3.9.16 - SpanMarker: 1.3.1.dev - Transformers: 4.33.0 - PyTorch: 2.0.1+cu118 - Datasets: 2.14.0 - Tokenizers: 0.13.2 ## Citation ### BibTeX ``` @software{Aarsen_SpanMarker, author = {Aarsen, Tom}, license = {Apache-2.0}, title = {{SpanMarker for Named Entity Recognition}}, url = {https://github.com/tomaarsen/SpanMarkerNER} } ```