model update

README.md

@@ -0,0 +1,176 @@
+---
+datasets:
+- tner/tweetner7
+metrics:
+- f1
+- precision
+- recall
+model-index:
+- name: tner/twitter-roberta-base-dec2020-tweetner7-2020-2021-concat
+  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: 0.6526255707762557
+    - name: Precision
+      type: precision
+      value: 0.6443868349864743
+    - name: Recall
+      type: recall
+      value: 0.6610777058279371
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.6069741859166096
+    - name: Precision (macro)
+      type: precision_macro
+      value: 0.5990170780704488
+    - name: Recall (macro)
+      type: recall_macro
+      value: 0.6172166732079049
+    - name: F1 (entity span)
+      type: f1_entity_span
+      value: 0.7868028997088875
+    - name: Precision (entity span)
+      type: precision_entity_span
+      value: 0.7768259693417493
+    - name: Recall (entity span)
+      type: recall_entity_span
+      value: 0.7970394356424193
+  - 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: 0.6544474393530997
+    - name: Precision
+      type: precision
+      value: 0.680874929893438
+    - name: Recall
+      type: recall
+      value: 0.6299948105864037
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.6138692748869267
+    - name: Precision (macro)
+      type: precision_macro
+      value: 0.639860659918586
+    - name: Recall (macro)
+      type: recall_macro
+      value: 0.5920548821120473
+    - name: F1 (entity span)
+      type: f1_entity_span
+      value: 0.7586950660555406
+    - name: Precision (entity span)
+      type: precision_entity_span
+      value: 0.7895622895622896
+    - name: Recall (entity span)
+      type: recall_entity_span
+      value: 0.7301504929942917
+
+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/twitter-roberta-base-dec2020-tweetner7-2020-2021-concat
+
+This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-dec2020](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2020) on the 
+[tner/tweetner7](https://huggingface.co/datasets/tner/tweetner7) dataset (`train_all` split).
+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): 0.6526255707762557
+- Precision (micro): 0.6443868349864743
+- Recall (micro): 0.6610777058279371
+- F1 (macro): 0.6069741859166096
+- Precision (macro): 0.5990170780704488
+- Recall (macro): 0.6172166732079049
+
+
+
+The per-entity breakdown of the F1 score on the test set are below:
+- corporation: 0.5153234960272418
+- creative_work: 0.47595252966895685
+- event: 0.46693657219973006
+- group: 0.60928
+- location: 0.6688567674113008
+- person: 0.8386501936197677
+- product: 0.6738197424892703 
+
+For F1 scores, the confidence interval is obtained by bootstrap as below:
+- F1 (micro): 
+    - 90%: [0.6437691693006731, 0.6623739817960804]
+    - 95%: [0.6423289413183693, 0.6642699129749126] 
+- F1 (macro): 
+    - 90%: [0.6437691693006731, 0.6623739817960804]
+    - 95%: [0.6423289413183693, 0.6642699129749126] 
+
+Full evaluation can be found at [metric file of NER](https://huggingface.co/tner/twitter-roberta-base-dec2020-tweetner7-2020-2021-concat/raw/main/eval/metric.json) 
+and [metric file of entity span](https://huggingface.co/tner/twitter-roberta-base-dec2020-tweetner7-2020-2021-concat/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/twitter-roberta-base-dec2020-tweetner7-2020-2021-concat")
+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_all
+ - dataset_name: None
+ - local_dataset: None
+ - model: cardiffnlp/twitter-roberta-base-dec2020
+ - crf: True
+ - max_length: 128
+ - epoch: 30
+ - batch_size: 32
+ - lr: 1e-05
+ - 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/twitter-roberta-base-dec2020-tweetner7-2020-2021-concat/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": 0.6425339366515838, "micro/f1_ci": {}, "micro/recall": 0.639, "micro/precision": 0.6461071789686552, "macro/f1": 0.5989569296686776, "macro/f1_ci": {}, "macro/recall": 0.5963672516044548, "macro/precision": 0.604043351645594, "per_entity_metric": {"corporation": {"f1": 0.6082474226804123, "f1_ci": {}, "precision": 0.6413043478260869, "recall": 0.5784313725490197}, "creative_work": {"f1": 0.4171779141104294, "f1_ci": {}, "precision": 0.38202247191011235, "recall": 0.4594594594594595}, "event": {"f1": 0.4251968503937008, "f1_ci": {}, "precision": 0.43902439024390244, "recall": 0.4122137404580153}, "group": {"f1": 0.6236080178173719, "f1_ci": {}, "precision": 0.6306306306306306, "recall": 0.6167400881057269}, "location": {"f1": 0.6486486486486486, "f1_ci": {}, "precision": 0.631578947368421, "recall": 0.6666666666666666}, "person": {"f1": 0.8286713286713286, "f1_ci": {}, "precision": 0.8200692041522492, "recall": 0.8374558303886925}, "product": {"f1": 0.6411483253588517, "f1_ci": {}, "precision": 0.6836734693877551, "recall": 0.6036036036036037}}}, "2021.test": {"micro/f1": 0.6526255707762557, "micro/f1_ci": {"90": [0.6437691693006731, 0.6623739817960804], "95": [0.6423289413183693, 0.6642699129749126]}, "micro/recall": 0.6610777058279371, "micro/precision": 0.6443868349864743, "macro/f1": 0.6069741859166096, "macro/f1_ci": {"90": [0.5969405931574795, 0.6169180905698453], "95": [0.5951882145650105, 0.6186261415221893]}, "macro/recall": 0.6172166732079049, "macro/precision": 0.5990170780704488, "per_entity_metric": {"corporation": {"f1": 0.5153234960272418, "f1_ci": {"90": [0.48979124830710313, 0.5416453967401038], "95": [0.4846763606289239, 0.5484286848323734]}, "precision": 0.5266821345707656, "recall": 0.5044444444444445}, "creative_work": {"f1": 0.47595252966895685, "f1_ci": {"90": [0.4450136547127212, 0.5060689375403542], "95": [0.4406451100516083, 0.5104259293002914]}, "precision": 0.4379310344827586, "recall": 0.521203830369357}, "event": {"f1": 0.46693657219973006, "f1_ci": {"90": [0.4433278746436782, 0.4904300531124057], "95": [0.43908609101602464, 0.4948272743714957]}, "precision": 0.46174377224199287, "recall": 0.47224749772520475}, "group": {"f1": 0.60928, "f1_ci": {"90": [0.58905038898122, 0.6306565075497464], "95": [0.5857818627333528, 0.6337814610823933]}, "precision": 0.5924082140634723, "recall": 0.6271409749670619}, "location": {"f1": 0.6688567674113008, "f1_ci": {"90": [0.6411061399494976, 0.6963439016627287], "95": [0.6362671616964405, 0.7015416924027178]}, "precision": 0.6315136476426799, "recall": 0.7108938547486033}, "person": {"f1": 0.8386501936197677, "f1_ci": {"90": [0.8280056803440087, 0.8493018351616476], "95": [0.8263492236736317, 0.8510733824274442]}, "precision": 0.8388048690520103, "recall": 0.838495575221239}, "product": {"f1": 0.6738197424892703, "f1_ci": {"90": [0.65218196906801, 0.6956179563127771], "95": [0.6475943730141744, 0.6984190719050953]}, "precision": 0.7040358744394619, "recall": 0.6460905349794238}}}, "2020.test": {"micro/f1": 0.6544474393530997, "micro/f1_ci": {"90": [0.6328497699075983, 0.6728044842641441], "95": [0.6291867061094695, 0.6760719350870426]}, "micro/recall": 0.6299948105864037, "micro/precision": 0.680874929893438, "macro/f1": 0.6138692748869267, "macro/f1_ci": {"90": [0.590175490065613, 0.6330937411191636], "95": [0.5865029961531653, 0.6369957089246945]}, "macro/recall": 0.5920548821120473, "macro/precision": 0.639860659918586, "per_entity_metric": {"corporation": {"f1": 0.5675675675675675, "f1_ci": {"90": [0.504295559145109, 0.6253295812135242], "95": [0.49554695181907565, 0.6339265479676438]}, "precision": 0.5865921787709497, "recall": 0.5497382198952879}, "creative_work": {"f1": 0.550561797752809, "f1_ci": {"90": [0.4934960481877372, 0.6020524118738404], "95": [0.4848118648722878, 0.6132814376651454]}, "precision": 0.5536723163841808, "recall": 0.547486033519553}, "event": {"f1": 0.462406015037594, "f1_ci": {"90": [0.4108194750550992, 0.5124638081746882], "95": [0.401291157260602, 0.5232811578406383]}, "precision": 0.4606741573033708, "recall": 0.4641509433962264}, "group": {"f1": 0.5551601423487544, "f1_ci": {"90": [0.5016589792385684, 0.6076091861210725], "95": [0.4912804447531413, 0.617329390460492]}, "precision": 0.6215139442231076, "recall": 0.5016077170418006}, "location": {"f1": 0.6426426426426426, "f1_ci": {"90": [0.5713889988128216, 0.7035890939799735], "95": [0.5591985171261487, 0.7202876984126986]}, "precision": 0.6369047619047619, "recall": 0.6484848484848484}, "person": {"f1": 0.8487467588591183, "f1_ci": {"90": [0.8219659833630422, 0.8716422802714063], "95": [0.8163611658762722, 0.8762541806020068]}, "precision": 0.875222816399287, "recall": 0.8238255033557047}, "product": {"f1": 0.67, "f1_ci": {"90": [0.6153665583243049, 0.7173996017258546], "95": [0.6060281385281385, 0.7304367192795584]}, "precision": 0.7444444444444445, "recall": 0.6090909090909091}}}, "2021.test (span detection)": {"micro/f1": 0.7868028997088875, "micro/f1_ci": {}, "micro/recall": 0.7970394356424193, "micro/precision": 0.7768259693417493, "macro/f1": 0.7868028997088875, "macro/f1_ci": {}, "macro/recall": 0.7970394356424193, "macro/precision": 0.7768259693417493}, "2020.test (span detection)": {"micro/f1": 0.7586950660555406, "micro/f1_ci": {}, "micro/recall": 0.7301504929942917, "micro/precision": 0.7895622895622896, "macro/f1": 0.7586950660555406, "macro/f1_ci": {}, "macro/recall": 0.7301504929942917, "macro/precision": 0.7895622895622896}}

eval/metric.test_2020.json

@@ -0,0 +1 @@
+{"micro/f1": 0.6544474393530997, "micro/f1_ci": {"90": [0.6328497699075983, 0.6728044842641441], "95": [0.6291867061094695, 0.6760719350870426]}, "micro/recall": 0.6299948105864037, "micro/precision": 0.680874929893438, "macro/f1": 0.6138692748869267, "macro/f1_ci": {"90": [0.590175490065613, 0.6330937411191636], "95": [0.5865029961531653, 0.6369957089246945]}, "macro/recall": 0.5920548821120473, "macro/precision": 0.639860659918586, "per_entity_metric": {"corporation": {"f1": 0.5675675675675675, "f1_ci": {"90": [0.504295559145109, 0.6253295812135242], "95": [0.49554695181907565, 0.6339265479676438]}, "precision": 0.5865921787709497, "recall": 0.5497382198952879}, "creative_work": {"f1": 0.550561797752809, "f1_ci": {"90": [0.4934960481877372, 0.6020524118738404], "95": [0.4848118648722878, 0.6132814376651454]}, "precision": 0.5536723163841808, "recall": 0.547486033519553}, "event": {"f1": 0.462406015037594, "f1_ci": {"90": [0.4108194750550992, 0.5124638081746882], "95": [0.401291157260602, 0.5232811578406383]}, "precision": 0.4606741573033708, "recall": 0.4641509433962264}, "group": {"f1": 0.5551601423487544, "f1_ci": {"90": [0.5016589792385684, 0.6076091861210725], "95": [0.4912804447531413, 0.617329390460492]}, "precision": 0.6215139442231076, "recall": 0.5016077170418006}, "location": {"f1": 0.6426426426426426, "f1_ci": {"90": [0.5713889988128216, 0.7035890939799735], "95": [0.5591985171261487, 0.7202876984126986]}, "precision": 0.6369047619047619, "recall": 0.6484848484848484}, "person": {"f1": 0.8487467588591183, "f1_ci": {"90": [0.8219659833630422, 0.8716422802714063], "95": [0.8163611658762722, 0.8762541806020068]}, "precision": 0.875222816399287, "recall": 0.8238255033557047}, "product": {"f1": 0.67, "f1_ci": {"90": [0.6153665583243049, 0.7173996017258546], "95": [0.6060281385281385, 0.7304367192795584]}, "precision": 0.7444444444444445, "recall": 0.6090909090909091}}}

eval/metric.test_2021.json

@@ -0,0 +1 @@
+{"micro/f1": 0.6526255707762557, "micro/f1_ci": {"90": [0.6437691693006731, 0.6623739817960804], "95": [0.6423289413183693, 0.6642699129749126]}, "micro/recall": 0.6610777058279371, "micro/precision": 0.6443868349864743, "macro/f1": 0.6069741859166096, "macro/f1_ci": {"90": [0.5969405931574795, 0.6169180905698453], "95": [0.5951882145650105, 0.6186261415221893]}, "macro/recall": 0.6172166732079049, "macro/precision": 0.5990170780704488, "per_entity_metric": {"corporation": {"f1": 0.5153234960272418, "f1_ci": {"90": [0.48979124830710313, 0.5416453967401038], "95": [0.4846763606289239, 0.5484286848323734]}, "precision": 0.5266821345707656, "recall": 0.5044444444444445}, "creative_work": {"f1": 0.47595252966895685, "f1_ci": {"90": [0.4450136547127212, 0.5060689375403542], "95": [0.4406451100516083, 0.5104259293002914]}, "precision": 0.4379310344827586, "recall": 0.521203830369357}, "event": {"f1": 0.46693657219973006, "f1_ci": {"90": [0.4433278746436782, 0.4904300531124057], "95": [0.43908609101602464, 0.4948272743714957]}, "precision": 0.46174377224199287, "recall": 0.47224749772520475}, "group": {"f1": 0.60928, "f1_ci": {"90": [0.58905038898122, 0.6306565075497464], "95": [0.5857818627333528, 0.6337814610823933]}, "precision": 0.5924082140634723, "recall": 0.6271409749670619}, "location": {"f1": 0.6688567674113008, "f1_ci": {"90": [0.6411061399494976, 0.6963439016627287], "95": [0.6362671616964405, 0.7015416924027178]}, "precision": 0.6315136476426799, "recall": 0.7108938547486033}, "person": {"f1": 0.8386501936197677, "f1_ci": {"90": [0.8280056803440087, 0.8493018351616476], "95": [0.8263492236736317, 0.8510733824274442]}, "precision": 0.8388048690520103, "recall": 0.838495575221239}, "product": {"f1": 0.6738197424892703, "f1_ci": {"90": [0.65218196906801, 0.6956179563127771], "95": [0.6475943730141744, 0.6984190719050953]}, "precision": 0.7040358744394619, "recall": 0.6460905349794238}}}

eval/metric_span.test_2020.json

@@ -0,0 +1 @@
+{"micro/f1": 0.7586950660555406, "micro/f1_ci": {}, "micro/recall": 0.7301504929942917, "micro/precision": 0.7895622895622896, "macro/f1": 0.7586950660555406, "macro/f1_ci": {}, "macro/recall": 0.7301504929942917, "macro/precision": 0.7895622895622896}

eval/metric_span.test_2021.json

@@ -0,0 +1 @@
+{"micro/f1": 0.7868028997088875, "micro/f1_ci": {}, "micro/recall": 0.7970394356424193, "micro/precision": 0.7768259693417493, "macro/f1": 0.7868028997088875, "macro/f1_ci": {}, "macro/recall": 0.7970394356424193, "macro/precision": 0.7768259693417493}

trainer_config.json

@@ -1 +1 @@
-{"data_split": "2020_2021.train", "model": "cardiffnlp/twitter-roberta-base-dec2020", "crf": true, "max_length": 128, "epoch": 30, "batch_size": 32, "lr": 1e-05, "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_all", "dataset_name": null, "local_dataset": null, "model": "cardiffnlp/twitter-roberta-base-dec2020", "crf": true, "max_length": 128, "epoch": 30, "batch_size": 32, "lr": 1e-05, "random_seed": 0, "gradient_accumulation_steps": 1, "weight_decay": 1e-07, "lr_warmup_step_ratio": 0.3, "max_grad_norm": 1}