model update

README.md

@@ -0,0 +1,176 @@
+---
+datasets:
+- tner/tweetner7
+metrics:
+- f1
+- precision
+- recall
+model-index:
+- name: tner/roberta-base-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: 0.6515831894070236
+    - name: Precision
+      type: precision
+      value: 0.6488190781930749
+    - name: Recall
+      type: recall
+      value: 0.6543709528214616
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.6081318073591985
+    - name: Precision (macro)
+      type: precision_macro
+      value: 0.6024892144112918
+    - name: Recall (macro)
+      type: recall_macro
+      value: 0.6155807376978756
+    - name: F1 (entity span)
+      type: f1_entity_span
+      value: 0.7893373251194657
+    - name: Precision (entity span)
+      type: precision_entity_span
+      value: 0.7859435909195138
+    - name: Recall (entity span)
+      type: recall_entity_span
+      value: 0.7927604949693535
+  - 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: 0.6531839300355288
+    - name: Precision
+      type: precision
+      value: 0.6899538106235565
+    - name: Recall
+      type: recall
+      value: 0.6201349247535028
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.6166186507300974
+    - name: Precision (macro)
+      type: precision_macro
+      value: 0.6523781324413148
+    - name: Recall (macro)
+      type: recall_macro
+      value: 0.5860926262979317
+    - name: F1 (entity span)
+      type: f1_entity_span
+      value: 0.7523236741388737
+    - name: Precision (entity span)
+      type: precision_entity_span
+      value: 0.7949162333911034
+    - name: Recall (entity span)
+      type: recall_entity_span
+      value: 0.7140633108458744
+
+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-base-tweetner7-2020-2021-concat
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) 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): 0.6515831894070236
+- Precision (micro): 0.6488190781930749
+- Recall (micro): 0.6543709528214616
+- F1 (macro): 0.6081318073591985
+- Precision (macro): 0.6024892144112918
+- Recall (macro): 0.6155807376978756
+
+
+
+The per-entity breakdown of the F1 score on the test set are below:
+- corporation: 0.5174234424498415
+- creative_work: 0.466403162055336
+- event: 0.46727272727272723
+- group: 0.6071197411003236
+- location: 0.6832786885245901
+- person: 0.8377301195672804
+- product: 0.6776947705442904 
+
+For F1 scores, the confidence interval is obtained by bootstrap as below:
+- F1 (micro): 
+    - 90%: [0.6426248846161623, 0.6611146727643068]
+    - 95%: [0.6408583849998567, 0.6629609445072536] 
+- F1 (macro): 
+    - 90%: [0.6426248846161623, 0.6611146727643068]
+    - 95%: [0.6408583849998567, 0.6629609445072536] 
+
+Full evaluation can be found at [metric file of NER](https://huggingface.co/tner/roberta-base-tweetner7-2020-2021-concat/raw/main/eval/metric.json) 
+and [metric file of entity span](https://huggingface.co/tner/roberta-base-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/roberta-base-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: roberta-base
+ - 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/roberta-base-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": 0.6469689251146206, "micro/f1_ci": {}, "micro/recall": 0.635, "micro/precision": 0.6593977154724818, "macro/f1": 0.6014288931166422, "macro/f1_ci": {}, "macro/recall": 0.5903596479194196, "macro/precision": 0.6143183232533814, "per_entity_metric": {"corporation": {"f1": 0.6019417475728156, "f1_ci": {}, "precision": 0.5961538461538461, "recall": 0.6078431372549019}, "creative_work": {"f1": 0.47887323943661975, "f1_ci": {}, "precision": 0.5, "recall": 0.4594594594594595}, "event": {"f1": 0.41767068273092367, "f1_ci": {}, "precision": 0.4406779661016949, "recall": 0.3969465648854962}, "group": {"f1": 0.631578947368421, "f1_ci": {}, "precision": 0.62882096069869, "recall": 0.6343612334801763}, "location": {"f1": 0.6122448979591836, "f1_ci": {}, "precision": 0.6, "recall": 0.625}, "person": {"f1": 0.8366247755834828, "f1_ci": {}, "precision": 0.8503649635036497, "recall": 0.823321554770318}, "product": {"f1": 0.6310679611650485, "f1_ci": {}, "precision": 0.6842105263157895, "recall": 0.5855855855855856}}}, "2021.test": {"micro/f1": 0.6515831894070236, "micro/f1_ci": {"90": [0.6426248846161623, 0.6611146727643068], "95": [0.6408583849998567, 0.6629609445072536]}, "micro/recall": 0.6543709528214616, "micro/precision": 0.6488190781930749, "macro/f1": 0.6081318073591985, "macro/f1_ci": {"90": [0.5982720247328263, 0.6181304060646944], "95": [0.5956407088917159, 0.6196130125852912]}, "macro/recall": 0.6155807376978756, "macro/precision": 0.6024892144112918, "per_entity_metric": {"corporation": {"f1": 0.5174234424498415, "f1_ci": {"90": [0.4936648515870705, 0.5437348601262041], "95": [0.4885022949243286, 0.5471504446094865]}, "precision": 0.49295774647887325, "recall": 0.5444444444444444}, "creative_work": {"f1": 0.466403162055336, "f1_ci": {"90": [0.4365426214916792, 0.49570670195121297], "95": [0.430553631074086, 0.5016692736109198]}, "precision": 0.4498094027954257, "recall": 0.4842681258549932}, "event": {"f1": 0.46727272727272723, "f1_ci": {"90": [0.4454429687968715, 0.4903171853702863], "95": [0.44099256614662297, 0.4949513525562855]}, "precision": 0.46684831970935514, "recall": 0.467697907188353}, "group": {"f1": 0.6071197411003236, "f1_ci": {"90": [0.5861576908243826, 0.6289925904123155], "95": [0.5836863413397794, 0.6323354921624595]}, "precision": 0.5966921119592875, "recall": 0.6179183135704874}, "location": {"f1": 0.6832786885245901, "f1_ci": {"90": [0.6571720974465681, 0.7109068486625629], "95": [0.6508663190665896, 0.7162931067002565]}, "precision": 0.6440049443757726, "recall": 0.7276536312849162}, "person": {"f1": 0.8377301195672804, "f1_ci": {"90": [0.8276980959235751, 0.8485767478830628], "95": [0.8260255921110556, 0.8508092332281014]}, "precision": 0.8631208447399296, "recall": 0.8137905604719764}, "product": {"f1": 0.6776947705442904, "f1_ci": {"90": [0.6553902251490492, 0.699632094409221], "95": [0.6517642249373523, 0.7046841960928648]}, "precision": 0.7039911308203991, "recall": 0.6532921810699589}}}, "2020.test": {"micro/f1": 0.6531839300355288, "micro/f1_ci": {"90": [0.6331939425228015, 0.6709196392454311], "95": [0.6287463050212823, 0.6742363307437226]}, "micro/recall": 0.6201349247535028, "micro/precision": 0.6899538106235565, "macro/f1": 0.6166186507300974, "macro/f1_ci": {"90": [0.594157548648219, 0.6362144855158252], "95": [0.5904501135575192, 0.639776197480569]}, "macro/recall": 0.5860926262979317, "macro/precision": 0.6523781324413148, "per_entity_metric": {"corporation": {"f1": 0.6194225721784777, "f1_ci": {"90": [0.5565017746228926, 0.6733323349589473], "95": [0.5479085471734517, 0.6820512820512821]}, "precision": 0.6210526315789474, "recall": 0.6178010471204188}, "creative_work": {"f1": 0.4894259818731118, "f1_ci": {"90": [0.4270354135925701, 0.545507399577167], "95": [0.41717142698274423, 0.5555627705627706]}, "precision": 0.5328947368421053, "recall": 0.45251396648044695}, "event": {"f1": 0.45136186770428016, "f1_ci": {"90": [0.3978736734522443, 0.501874083251449], "95": [0.3891742854740079, 0.510803537621031]}, "precision": 0.46586345381526106, "recall": 0.4377358490566038}, "group": {"f1": 0.5658362989323844, "f1_ci": {"90": [0.5151382476251127, 0.61462698148764], "95": [0.5076307180164151, 0.626772526987192]}, "precision": 0.6334661354581673, "recall": 0.5112540192926045}, "location": {"f1": 0.6894409937888198, "f1_ci": {"90": [0.6274217149546386, 0.7440886398547689], "95": [0.6148768819473758, 0.7561225667461723]}, "precision": 0.7070063694267515, "recall": 0.6727272727272727}, "person": {"f1": 0.8275261324041812, "f1_ci": {"90": [0.7993567425754086, 0.8511074607796776], "95": [0.7958273985244123, 0.8545669887000585]}, "precision": 0.8605072463768116, "recall": 0.7969798657718121}, "product": {"f1": 0.6733167082294264, "f1_ci": {"90": [0.6190924641557551, 0.723014061091403], "95": [0.6093323046153235, 0.7345134333722708]}, "precision": 0.7458563535911602, "recall": 0.6136363636363636}}}, "2021.test (span detection)": {"micro/f1": 0.7893373251194657, "micro/f1_ci": {}, "micro/recall": 0.7927604949693535, "micro/precision": 0.7859435909195138, "macro/f1": 0.7893373251194657, "macro/f1_ci": {}, "macro/recall": 0.7927604949693535, "macro/precision": 0.7859435909195138}, "2020.test (span detection)": {"micro/f1": 0.7523236741388737, "micro/f1_ci": {}, "micro/recall": 0.7140633108458744, "micro/precision": 0.7949162333911034, "macro/f1": 0.7523236741388737, "macro/f1_ci": {}, "macro/recall": 0.7140633108458744, "macro/precision": 0.7949162333911034}}

eval/metric.test_2020.json

@@ -0,0 +1 @@
+{"micro/f1": 0.6531839300355288, "micro/f1_ci": {"90": [0.6331939425228015, 0.6709196392454311], "95": [0.6287463050212823, 0.6742363307437226]}, "micro/recall": 0.6201349247535028, "micro/precision": 0.6899538106235565, "macro/f1": 0.6166186507300974, "macro/f1_ci": {"90": [0.594157548648219, 0.6362144855158252], "95": [0.5904501135575192, 0.639776197480569]}, "macro/recall": 0.5860926262979317, "macro/precision": 0.6523781324413148, "per_entity_metric": {"corporation": {"f1": 0.6194225721784777, "f1_ci": {"90": [0.5565017746228926, 0.6733323349589473], "95": [0.5479085471734517, 0.6820512820512821]}, "precision": 0.6210526315789474, "recall": 0.6178010471204188}, "creative_work": {"f1": 0.4894259818731118, "f1_ci": {"90": [0.4270354135925701, 0.545507399577167], "95": [0.41717142698274423, 0.5555627705627706]}, "precision": 0.5328947368421053, "recall": 0.45251396648044695}, "event": {"f1": 0.45136186770428016, "f1_ci": {"90": [0.3978736734522443, 0.501874083251449], "95": [0.3891742854740079, 0.510803537621031]}, "precision": 0.46586345381526106, "recall": 0.4377358490566038}, "group": {"f1": 0.5658362989323844, "f1_ci": {"90": [0.5151382476251127, 0.61462698148764], "95": [0.5076307180164151, 0.626772526987192]}, "precision": 0.6334661354581673, "recall": 0.5112540192926045}, "location": {"f1": 0.6894409937888198, "f1_ci": {"90": [0.6274217149546386, 0.7440886398547689], "95": [0.6148768819473758, 0.7561225667461723]}, "precision": 0.7070063694267515, "recall": 0.6727272727272727}, "person": {"f1": 0.8275261324041812, "f1_ci": {"90": [0.7993567425754086, 0.8511074607796776], "95": [0.7958273985244123, 0.8545669887000585]}, "precision": 0.8605072463768116, "recall": 0.7969798657718121}, "product": {"f1": 0.6733167082294264, "f1_ci": {"90": [0.6190924641557551, 0.723014061091403], "95": [0.6093323046153235, 0.7345134333722708]}, "precision": 0.7458563535911602, "recall": 0.6136363636363636}}}

eval/metric.test_2021.json

@@ -0,0 +1 @@
+{"micro/f1": 0.6515831894070236, "micro/f1_ci": {"90": [0.6426248846161623, 0.6611146727643068], "95": [0.6408583849998567, 0.6629609445072536]}, "micro/recall": 0.6543709528214616, "micro/precision": 0.6488190781930749, "macro/f1": 0.6081318073591985, "macro/f1_ci": {"90": [0.5982720247328263, 0.6181304060646944], "95": [0.5956407088917159, 0.6196130125852912]}, "macro/recall": 0.6155807376978756, "macro/precision": 0.6024892144112918, "per_entity_metric": {"corporation": {"f1": 0.5174234424498415, "f1_ci": {"90": [0.4936648515870705, 0.5437348601262041], "95": [0.4885022949243286, 0.5471504446094865]}, "precision": 0.49295774647887325, "recall": 0.5444444444444444}, "creative_work": {"f1": 0.466403162055336, "f1_ci": {"90": [0.4365426214916792, 0.49570670195121297], "95": [0.430553631074086, 0.5016692736109198]}, "precision": 0.4498094027954257, "recall": 0.4842681258549932}, "event": {"f1": 0.46727272727272723, "f1_ci": {"90": [0.4454429687968715, 0.4903171853702863], "95": [0.44099256614662297, 0.4949513525562855]}, "precision": 0.46684831970935514, "recall": 0.467697907188353}, "group": {"f1": 0.6071197411003236, "f1_ci": {"90": [0.5861576908243826, 0.6289925904123155], "95": [0.5836863413397794, 0.6323354921624595]}, "precision": 0.5966921119592875, "recall": 0.6179183135704874}, "location": {"f1": 0.6832786885245901, "f1_ci": {"90": [0.6571720974465681, 0.7109068486625629], "95": [0.6508663190665896, 0.7162931067002565]}, "precision": 0.6440049443757726, "recall": 0.7276536312849162}, "person": {"f1": 0.8377301195672804, "f1_ci": {"90": [0.8276980959235751, 0.8485767478830628], "95": [0.8260255921110556, 0.8508092332281014]}, "precision": 0.8631208447399296, "recall": 0.8137905604719764}, "product": {"f1": 0.6776947705442904, "f1_ci": {"90": [0.6553902251490492, 0.699632094409221], "95": [0.6517642249373523, 0.7046841960928648]}, "precision": 0.7039911308203991, "recall": 0.6532921810699589}}}

eval/metric_span.test_2020.json

@@ -0,0 +1 @@
+{"micro/f1": 0.7523236741388737, "micro/f1_ci": {}, "micro/recall": 0.7140633108458744, "micro/precision": 0.7949162333911034, "macro/f1": 0.7523236741388737, "macro/f1_ci": {}, "macro/recall": 0.7140633108458744, "macro/precision": 0.7949162333911034}

eval/metric_span.test_2021.json

@@ -0,0 +1 @@
+{"micro/f1": 0.7893373251194657, "micro/f1_ci": {}, "micro/recall": 0.7927604949693535, "micro/precision": 0.7859435909195138, "macro/f1": 0.7893373251194657, "macro/f1_ci": {}, "macro/recall": 0.7927604949693535, "macro/precision": 0.7859435909195138}

trainer_config.json

@@ -1 +1 @@
-{"data_split": "2020_2021.train", "model": "roberta-base", "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": "roberta-base", "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}