asahi417 commited on
Commit
fb9fb5c
1 Parent(s): 8b43b8d

model update

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -6,7 +6,7 @@ metrics:
6
  - precision
7
  - recall
8
  model-index:
9
- - name: tner/twitter-roberta-base-2019-90m-tweetner7-2020-2021-continuous
10
  results:
11
  - task:
12
  name: Token Classification
@@ -76,7 +76,7 @@ widget:
76
  - text: "Get the all-analog Classic Vinyl Edition of `Takin' Off` Album from {{@Herbie Hancock@}} via {{USERNAME}} link below: {{URL}}"
77
  example_title: "NER Example 1"
78
  ---
79
- # tner/twitter-roberta-base-2019-90m-tweetner7-2020-2021-continuous
80
 
81
  This model is a fine-tuned version of [tner/twitter-roberta-base-2019-90m-tweetner-2020](https://huggingface.co/tner/twitter-roberta-base-2019-90m-tweetner-2020) on the
82
  [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`.
@@ -108,8 +108,8 @@ For F1 scores, the confidence interval is obtained by bootstrap as below:
108
  - 90%: [0.6500084574752211, 0.6675327789934176]
109
  - 95%: [0.6480876172354417, 0.6695072839398589]
110
 
111
- Full evaluation can be found at [metric file of NER](https://huggingface.co/tner/twitter-roberta-base-2019-90m-tweetner7-2020-2021-continuous/raw/main/eval/metric.json)
112
- and [metric file of entity span](https://huggingface.co/tner/twitter-roberta-base-2019-90m-tweetner7-2020-2021-continuous/raw/main/eval/metric_span.json).
113
 
114
  ### Usage
115
  This model can be used through the [tner library](https://github.com/asahi417/tner). Install the library via pip
@@ -119,7 +119,7 @@ pip install tner
119
  and activate model as below.
120
  ```python
121
  from tner import TransformersNER
122
- model = TransformersNER("tner/twitter-roberta-base-2019-90m-tweetner7-2020-2021-continuous")
123
  model.predict(["Jacob Collier is a Grammy awarded English artist from London"])
124
  ```
125
  It can be used via transformers library but it is not recommended as CRF layer is not supported at the moment.
@@ -143,7 +143,7 @@ The following hyperparameters were used during training:
143
  - lr_warmup_step_ratio: 0.3
144
  - max_grad_norm: 1
145
 
146
- The full configuration can be found at [fine-tuning parameter file](https://huggingface.co/tner/twitter-roberta-base-2019-90m-tweetner7-2020-2021-continuous/raw/main/trainer_config.json).
147
 
148
  ### Reference
149
  If you use any resource from T-NER, please consider to cite our [paper](https://aclanthology.org/2021.eacl-demos.7/).
 
6
  - precision
7
  - recall
8
  model-index:
9
+ - name: tner/twitter-roberta-base-2019-90m-tweetner7-continuous
10
  results:
11
  - task:
12
  name: Token Classification
 
76
  - text: "Get the all-analog Classic Vinyl Edition of `Takin' Off` Album from {{@Herbie Hancock@}} via {{USERNAME}} link below: {{URL}}"
77
  example_title: "NER Example 1"
78
  ---
79
+ # tner/twitter-roberta-base-2019-90m-tweetner7-continuous
80
 
81
  This model is a fine-tuned version of [tner/twitter-roberta-base-2019-90m-tweetner-2020](https://huggingface.co/tner/twitter-roberta-base-2019-90m-tweetner-2020) on the
82
  [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`.
 
108
  - 90%: [0.6500084574752211, 0.6675327789934176]
109
  - 95%: [0.6480876172354417, 0.6695072839398589]
110
 
111
+ Full evaluation can be found at [metric file of NER](https://huggingface.co/tner/twitter-roberta-base-2019-90m-tweetner7-continuous/raw/main/eval/metric.json)
112
+ and [metric file of entity span](https://huggingface.co/tner/twitter-roberta-base-2019-90m-tweetner7-continuous/raw/main/eval/metric_span.json).
113
 
114
  ### Usage
115
  This model can be used through the [tner library](https://github.com/asahi417/tner). Install the library via pip
 
119
  and activate model as below.
120
  ```python
121
  from tner import TransformersNER
122
+ model = TransformersNER("tner/twitter-roberta-base-2019-90m-tweetner7-continuous")
123
  model.predict(["Jacob Collier is a Grammy awarded English artist from London"])
124
  ```
125
  It can be used via transformers library but it is not recommended as CRF layer is not supported at the moment.
 
143
  - lr_warmup_step_ratio: 0.3
144
  - max_grad_norm: 1
145
 
146
+ The full configuration can be found at [fine-tuning parameter file](https://huggingface.co/tner/twitter-roberta-base-2019-90m-tweetner7-continuous/raw/main/trainer_config.json).
147
 
148
  ### Reference
149
  If you use any resource from T-NER, please consider to cite our [paper](https://aclanthology.org/2021.eacl-demos.7/).