model update

README.md

@@ -0,0 +1,176 @@
+---
+datasets:
+- tner/tweetner7
+metrics:
+- f1
+- precision
+- recall
+model-index:
+- name: tner/roberta-large-tweetner7-2020-2021-continuous
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: tner/tweetner7/test_2021
+      type: tner/tweetner7/test_2021
+      args: tner/tweetner7/test_2021
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.6602098466505246
+    - name: Precision
+      type: precision
+      value: 0.6583122556909634
+    - name: Recall
+      type: recall
+      value: 0.6621184088806661
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.6089541397781462
+    - name: Precision (macro)
+      type: precision_macro
+      value: 0.6063426866310634
+    - name: Recall (macro)
+      type: recall_macro
+      value: 0.6145764579798109
+    - name: F1 (entity span)
+      type: f1_entity_span
+      value: 0.791351974632459
+    - name: Precision (entity span)
+      type: precision_entity_span
+      value: 0.78903196137043
+    - name: Recall (entity span)
+      type: recall_entity_span
+      value: 0.7936856713310975
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: tner/tweetner7/test_2020
+      type: tner/tweetner7/test_2020
+      args: tner/tweetner7/test_2020
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.6626406807576174
+    - name: Precision
+      type: precision
+      value: 0.7033799533799534
+    - name: Recall
+      type: recall
+      value: 0.6263622210690192
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.6239587887403221
+    - name: Precision (macro)
+      type: precision_macro
+      value: 0.6646899818440488
+    - name: Recall (macro)
+      type: recall_macro
+      value: 0.5921933163664825
+    - name: F1 (entity span)
+      type: f1_entity_span
+      value: 0.7644151565074135
+    - name: Precision (entity span)
+      type: precision_entity_span
+      value: 0.8116618075801749
+    - name: Recall (entity span)
+      type: recall_entity_span
+      value: 0.7223663725998962
+
+pipeline_tag: token-classification
+widget:
+- text: "Get the all-analog Classic Vinyl Edition of `Takin' Off` Album from {{@Herbie Hancock@}} via {{USERNAME}} link below: {{URL}}"
+  example_title: "NER Example 1"
+---
+# tner/roberta-large-tweetner7-2020-2021-continuous
+
+This model is a fine-tuned version of [tner/roberta-large-tweetner-2020](https://huggingface.co/tner/roberta-large-tweetner-2020) on the 
+[tner/tweetner7](https://huggingface.co/datasets/tner/tweetner7) dataset (`train_2021` split). The model is first fine-tuned on `train_2020`, and then continuously fine-tuned on `train_2021`. 
+Model fine-tuning is done via [T-NER](https://github.com/asahi417/tner)'s hyper-parameter search (see the repository
+for more detail). It achieves the following results on the test set of 2021:
+- F1 (micro): 0.6602098466505246
+- Precision (micro): 0.6583122556909634
+- Recall (micro): 0.6621184088806661
+- F1 (macro): 0.6089541397781462
+- Precision (macro): 0.6063426866310634
+- Recall (macro): 0.6145764579798109
+
+
+
+The per-entity breakdown of the F1 score on the test set are below:
+- corporation: 0.5315217391304348
+- creative_work: 0.44416243654822335
+- event: 0.48787728847105394
+- group: 0.6115476597198496
+- location: 0.6740692357935989
+- person: 0.8471820809248555
+- product: 0.6663185378590079 
+
+For F1 scores, the confidence interval is obtained by bootstrap as below:
+- F1 (micro): 
+    - 90%: [0.6517159585889167, 0.6692301926939467]
+    - 95%: [0.6493037560449608, 0.6705545707079725] 
+- F1 (macro): 
+    - 90%: [0.6517159585889167, 0.6692301926939467]
+    - 95%: [0.6493037560449608, 0.6705545707079725] 
+
+Full evaluation can be found at [metric file of NER](https://huggingface.co/tner/roberta-large-tweetner7-2020-2021-continuous/raw/main/eval/metric.json) 
+and [metric file of entity span](https://huggingface.co/tner/roberta-large-tweetner7-2020-2021-continuous/raw/main/eval/metric_span.json).
+
+### Usage
+This model can be used through the [tner library](https://github.com/asahi417/tner). Install the library via pip   
+```shell
+pip install tner
+```
+and activate model as below.
+```python
+from tner import TransformersNER
+model = TransformersNER("tner/roberta-large-tweetner7-2020-2021-continuous")
+model.predict(["Jacob Collier is a Grammy awarded English artist from London"])
+```
+It can be used via transformers library but it is not recommended as CRF layer is not supported at the moment.
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+ - dataset: ['tner/tweetner7']
+ - dataset_split: train_2021
+ - dataset_name: None
+ - local_dataset: None
+ - model: tner/roberta-large-tweetner-2020
+ - crf: True
+ - max_length: 128
+ - epoch: 30
+ - batch_size: 32
+ - lr: 1e-06
+ - random_seed: 0
+ - gradient_accumulation_steps: 1
+ - weight_decay: 1e-07
+ - lr_warmup_step_ratio: 0.3
+ - max_grad_norm: 1
+
+The full configuration can be found at [fine-tuning parameter file](https://huggingface.co/tner/roberta-large-tweetner7-2020-2021-continuous/raw/main/trainer_config.json).
+
+### Reference
+If you use any resource from T-NER, please consider to cite our [paper](https://aclanthology.org/2021.eacl-demos.7/).
+
+```
+
+@inproceedings{ushio-camacho-collados-2021-ner,
+    title = "{T}-{NER}: An All-Round Python Library for Transformer-based Named Entity Recognition",
+    author = "Ushio, Asahi  and
+      Camacho-Collados, Jose",
+    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
+    month = apr,
+    year = "2021",
+    address = "Online",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2021.eacl-demos.7",
+    doi = "10.18653/v1/2021.eacl-demos.7",
+    pages = "53--62",
+    abstract = "Language model (LM) pretraining has led to consistent improvements in many NLP downstream tasks, including named entity recognition (NER). In this paper, we present T-NER (Transformer-based Named Entity Recognition), a Python library for NER LM finetuning. In addition to its practical utility, T-NER facilitates the study and investigation of the cross-domain and cross-lingual generalization ability of LMs finetuned on NER. Our library also provides a web app where users can get model predictions interactively for arbitrary text, which facilitates qualitative model evaluation for non-expert programmers. We show the potential of the library by compiling nine public NER datasets into a unified format and evaluating the cross-domain and cross- lingual performance across the datasets. The results from our initial experiments show that in-domain performance is generally competitive across datasets. However, cross-domain generalization is challenging even with a large pretrained LM, which has nevertheless capacity to learn domain-specific features if fine- tuned on a combined dataset. To facilitate future research, we also release all our LM checkpoints via the Hugging Face model hub.",
+}
+
+```

eval/metric.json

@@ -1 +0,0 @@
-{"2021.dev": {"micro/f1": 0.6493638676844784, "micro/f1_ci": {}, "micro/recall": 0.638, "micro/precision": 0.661139896373057, "macro/f1": 0.6064563940502387, "macro/f1_ci": {}, "macro/recall": 0.5954284242860318, "macro/precision": 0.6210253991075032, "per_entity_metric": {"corporation": {"f1": 0.5797101449275363, "f1_ci": {}, "precision": 0.5714285714285714, "recall": 0.5882352941176471}, "creative_work": {"f1": 0.4805194805194805, "f1_ci": {}, "precision": 0.4625, "recall": 0.5}, "event": {"f1": 0.4472573839662447, "f1_ci": {}, "precision": 0.5, "recall": 0.40458015267175573}, "group": {"f1": 0.6340326340326341, "f1_ci": {}, "precision": 0.6732673267326733, "recall": 0.5991189427312775}, "location": {"f1": 0.676470588235294, "f1_ci": {}, "precision": 0.71875, "recall": 0.6388888888888888}, "person": {"f1": 0.8197278911564626, "f1_ci": {}, "precision": 0.7901639344262295, "recall": 0.8515901060070671}, "product": {"f1": 0.6074766355140188, "f1_ci": {}, "precision": 0.6310679611650486, "recall": 0.5855855855855856}}}, "2021.test": {"micro/f1": 0.6602098466505246, "micro/f1_ci": {"90": [0.6517159585889167, 0.6692301926939467], "95": [0.6493037560449608, 0.6705545707079725]}, "micro/recall": 0.6621184088806661, "micro/precision": 0.6583122556909634, "macro/f1": 0.6089541397781462, "macro/f1_ci": {"90": [0.5992124192664839, 0.6181423707734851], "95": [0.5972392466243823, 0.6207098127019401]}, "macro/recall": 0.6145764579798109, "macro/precision": 0.6063426866310634, "per_entity_metric": {"corporation": {"f1": 0.5315217391304348, "f1_ci": {"90": [0.5062037953042462, 0.557002893455922], "95": [0.5029997910370321, 0.5630029363336992]}, "precision": 0.5202127659574468, "recall": 0.5433333333333333}, "creative_work": {"f1": 0.44416243654822335, "f1_ci": {"90": [0.4122197188872424, 0.47462918144124866], "95": [0.406035622185493, 0.4795]}, "precision": 0.41420118343195267, "recall": 0.478796169630643}, "event": {"f1": 0.48787728847105394, "f1_ci": {"90": [0.4644448167194252, 0.5105902072328322], "95": [0.45939395779891246, 0.5167725537147063]}, "precision": 0.53470715835141, "recall": 0.44858962693357596}, "group": {"f1": 0.6115476597198496, "f1_ci": {"90": [0.5919094922318341, 0.6339441441403232], "95": [0.5886699796091751, 0.639161660780465]}, "precision": 0.6352022711142654, "recall": 0.5895915678524374}, "location": {"f1": 0.6740692357935989, "f1_ci": {"90": [0.6463384301732925, 0.6996206891806976], "95": [0.6399452184154117, 0.704592239580396]}, "precision": 0.6331288343558282, "recall": 0.7206703910614525}, "person": {"f1": 0.8471820809248555, "f1_ci": {"90": [0.8364545587859473, 0.8578287867782268], "95": [0.8343356681910271, 0.8597832152335898]}, "precision": 0.8303824362606232, "recall": 0.8646755162241888}, "product": {"f1": 0.6663185378590079, "f1_ci": {"90": [0.6430440201857166, 0.6880601156195403], "95": [0.6389027898322917, 0.6912792458554788]}, "precision": 0.6765641569459173, "recall": 0.6563786008230452}}}, "2020.test": {"micro/f1": 0.6626406807576174, "micro/f1_ci": {"90": [0.6421811481777288, 0.6824408527817176], "95": [0.6372901150251117, 0.6854804698319146]}, "micro/recall": 0.6263622210690192, "micro/precision": 0.7033799533799534, "macro/f1": 0.6239587887403221, "macro/f1_ci": {"90": [0.602302727331785, 0.6450629596325671], "95": [0.5970260956556793, 0.6489300269035955]}, "macro/recall": 0.5921933163664825, "macro/precision": 0.6646899818440488, "per_entity_metric": {"corporation": {"f1": 0.5775401069518716, "f1_ci": {"90": [0.5159532401719902, 0.631592039800995], "95": [0.5048681813824177, 0.6443506817426007]}, "precision": 0.5901639344262295, "recall": 0.5654450261780105}, "creative_work": {"f1": 0.5414364640883977, "f1_ci": {"90": [0.48183509569087224, 0.5982905982905983], "95": [0.47114785318559554, 0.6071453442101075]}, "precision": 0.5355191256830601, "recall": 0.547486033519553}, "event": {"f1": 0.4848484848484848, "f1_ci": {"90": [0.430196666372696, 0.5392663954742951], "95": [0.41777510040160637, 0.5480195121951219]}, "precision": 0.5217391304347826, "recall": 0.4528301886792453}, "group": {"f1": 0.5752380952380952, "f1_ci": {"90": [0.5250448836936347, 0.6279727523503913], "95": [0.5077881926419612, 0.6401626025391906]}, "precision": 0.705607476635514, "recall": 0.4855305466237942}, "location": {"f1": 0.676923076923077, "f1_ci": {"90": [0.6140042598509052, 0.7335108890745321], "95": [0.6034973885094416, 0.7419877793680504]}, "precision": 0.6875, "recall": 0.6666666666666666}, "person": {"f1": 0.8333333333333334, "f1_ci": {"90": [0.8072107474406325, 0.8569065343258891], "95": [0.8017923571846364, 0.8613520685620369]}, "precision": 0.8538732394366197, "recall": 0.8137583892617449}, "product": {"f1": 0.6783919597989949, "f1_ci": {"90": [0.6273530339040599, 0.7267773646555122], "95": [0.6158022378645676, 0.7371281899611289]}, "precision": 0.7584269662921348, "recall": 0.6136363636363636}}}, "2021.test (span detection)": {"micro/f1": 0.791351974632459, "micro/f1_ci": {}, "micro/recall": 0.7936856713310975, "micro/precision": 0.78903196137043, "macro/f1": 0.791351974632459, "macro/f1_ci": {}, "macro/recall": 0.7936856713310975, "macro/precision": 0.78903196137043}, "2020.test (span detection)": {"micro/f1": 0.7644151565074135, "micro/f1_ci": {}, "micro/recall": 0.7223663725998962, "micro/precision": 0.8116618075801749, "macro/f1": 0.7644151565074135, "macro/f1_ci": {}, "macro/recall": 0.7223663725998962, "macro/precision": 0.8116618075801749}}

eval/metric.test_2020.json

@@ -0,0 +1 @@
+{"micro/f1": 0.6626406807576174, "micro/f1_ci": {"90": [0.6421811481777288, 0.6824408527817176], "95": [0.6372901150251117, 0.6854804698319146]}, "micro/recall": 0.6263622210690192, "micro/precision": 0.7033799533799534, "macro/f1": 0.6239587887403221, "macro/f1_ci": {"90": [0.602302727331785, 0.6450629596325671], "95": [0.5970260956556793, 0.6489300269035955]}, "macro/recall": 0.5921933163664825, "macro/precision": 0.6646899818440488, "per_entity_metric": {"corporation": {"f1": 0.5775401069518716, "f1_ci": {"90": [0.5159532401719902, 0.631592039800995], "95": [0.5048681813824177, 0.6443506817426007]}, "precision": 0.5901639344262295, "recall": 0.5654450261780105}, "creative_work": {"f1": 0.5414364640883977, "f1_ci": {"90": [0.48183509569087224, 0.5982905982905983], "95": [0.47114785318559554, 0.6071453442101075]}, "precision": 0.5355191256830601, "recall": 0.547486033519553}, "event": {"f1": 0.4848484848484848, "f1_ci": {"90": [0.430196666372696, 0.5392663954742951], "95": [0.41777510040160637, 0.5480195121951219]}, "precision": 0.5217391304347826, "recall": 0.4528301886792453}, "group": {"f1": 0.5752380952380952, "f1_ci": {"90": [0.5250448836936347, 0.6279727523503913], "95": [0.5077881926419612, 0.6401626025391906]}, "precision": 0.705607476635514, "recall": 0.4855305466237942}, "location": {"f1": 0.676923076923077, "f1_ci": {"90": [0.6140042598509052, 0.7335108890745321], "95": [0.6034973885094416, 0.7419877793680504]}, "precision": 0.6875, "recall": 0.6666666666666666}, "person": {"f1": 0.8333333333333334, "f1_ci": {"90": [0.8072107474406325, 0.8569065343258891], "95": [0.8017923571846364, 0.8613520685620369]}, "precision": 0.8538732394366197, "recall": 0.8137583892617449}, "product": {"f1": 0.6783919597989949, "f1_ci": {"90": [0.6273530339040599, 0.7267773646555122], "95": [0.6158022378645676, 0.7371281899611289]}, "precision": 0.7584269662921348, "recall": 0.6136363636363636}}}

eval/metric.test_2021.json

@@ -0,0 +1 @@
+{"micro/f1": 0.6602098466505246, "micro/f1_ci": {"90": [0.6517159585889167, 0.6692301926939467], "95": [0.6493037560449608, 0.6705545707079725]}, "micro/recall": 0.6621184088806661, "micro/precision": 0.6583122556909634, "macro/f1": 0.6089541397781462, "macro/f1_ci": {"90": [0.5992124192664839, 0.6181423707734851], "95": [0.5972392466243823, 0.6207098127019401]}, "macro/recall": 0.6145764579798109, "macro/precision": 0.6063426866310634, "per_entity_metric": {"corporation": {"f1": 0.5315217391304348, "f1_ci": {"90": [0.5062037953042462, 0.557002893455922], "95": [0.5029997910370321, 0.5630029363336992]}, "precision": 0.5202127659574468, "recall": 0.5433333333333333}, "creative_work": {"f1": 0.44416243654822335, "f1_ci": {"90": [0.4122197188872424, 0.47462918144124866], "95": [0.406035622185493, 0.4795]}, "precision": 0.41420118343195267, "recall": 0.478796169630643}, "event": {"f1": 0.48787728847105394, "f1_ci": {"90": [0.4644448167194252, 0.5105902072328322], "95": [0.45939395779891246, 0.5167725537147063]}, "precision": 0.53470715835141, "recall": 0.44858962693357596}, "group": {"f1": 0.6115476597198496, "f1_ci": {"90": [0.5919094922318341, 0.6339441441403232], "95": [0.5886699796091751, 0.639161660780465]}, "precision": 0.6352022711142654, "recall": 0.5895915678524374}, "location": {"f1": 0.6740692357935989, "f1_ci": {"90": [0.6463384301732925, 0.6996206891806976], "95": [0.6399452184154117, 0.704592239580396]}, "precision": 0.6331288343558282, "recall": 0.7206703910614525}, "person": {"f1": 0.8471820809248555, "f1_ci": {"90": [0.8364545587859473, 0.8578287867782268], "95": [0.8343356681910271, 0.8597832152335898]}, "precision": 0.8303824362606232, "recall": 0.8646755162241888}, "product": {"f1": 0.6663185378590079, "f1_ci": {"90": [0.6430440201857166, 0.6880601156195403], "95": [0.6389027898322917, 0.6912792458554788]}, "precision": 0.6765641569459173, "recall": 0.6563786008230452}}}

eval/metric_span.test_2020.json

@@ -0,0 +1 @@
+{"micro/f1": 0.7644151565074135, "micro/f1_ci": {}, "micro/recall": 0.7223663725998962, "micro/precision": 0.8116618075801749, "macro/f1": 0.7644151565074135, "macro/f1_ci": {}, "macro/recall": 0.7223663725998962, "macro/precision": 0.8116618075801749}

eval/metric_span.test_2021.json

@@ -0,0 +1 @@
+{"micro/f1": 0.791351974632459, "micro/f1_ci": {}, "micro/recall": 0.7936856713310975, "micro/precision": 0.78903196137043, "macro/f1": 0.791351974632459, "macro/f1_ci": {}, "macro/recall": 0.7936856713310975, "macro/precision": 0.78903196137043}

trainer_config.json

@@ -1 +1 @@
-{"data_split": "2021.train", "model": "tner/roberta-large-tweetner-2020", "crf": true, "max_length": 128, "epoch": 30, "batch_size": 32, "lr": 1e-06, "random_seed": 0, "gradient_accumulation_steps": 1, "weight_decay": 1e-07, "lr_warmup_step_ratio": 0.3, "max_grad_norm": 1}
+{"dataset": ["tner/tweetner7"], "dataset_split": "train_2021", "dataset_name": null, "local_dataset": null, "model": "tner/roberta-large-tweetner-2020", "crf": true, "max_length": 128, "epoch": 30, "batch_size": 32, "lr": 1e-06, "random_seed": 0, "gradient_accumulation_steps": 1, "weight_decay": 1e-07, "lr_warmup_step_ratio": 0.3, "max_grad_norm": 1}