model update
Browse files- README.md +176 -0
- eval/metric.test_2020.json +1 -0
- eval/{metric.json → metric.test_2021.json} +1 -1
- eval/metric_span.test_2020.json +1 -0
- eval/metric_span.test_2021.json +1 -0
- eval/prediction.2020.test.json +0 -0
- eval/prediction.2021.dev.json +0 -0
- eval/prediction.2021.test.json +0 -0
- trainer_config.json +1 -1
README.md
ADDED
@@ -0,0 +1,176 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
datasets:
|
3 |
+
- tner/tweetner7
|
4 |
+
metrics:
|
5 |
+
- f1
|
6 |
+
- precision
|
7 |
+
- recall
|
8 |
+
model-index:
|
9 |
+
- name: tner/bertweet-base-tweetner7-2020-2021-continuous
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Token Classification
|
13 |
+
type: token-classification
|
14 |
+
dataset:
|
15 |
+
name: tner/tweetner7/test_2021
|
16 |
+
type: tner/tweetner7/test_2021
|
17 |
+
args: tner/tweetner7/test_2021
|
18 |
+
metrics:
|
19 |
+
- name: F1
|
20 |
+
type: f1
|
21 |
+
value: 0.6584472230299506
|
22 |
+
- name: Precision
|
23 |
+
type: precision
|
24 |
+
value: 0.6623376623376623
|
25 |
+
- name: Recall
|
26 |
+
type: recall
|
27 |
+
value: 0.6546022201665125
|
28 |
+
- name: F1 (macro)
|
29 |
+
type: f1_macro
|
30 |
+
value: 0.6102300887168732
|
31 |
+
- name: Precision (macro)
|
32 |
+
type: precision_macro
|
33 |
+
value: 0.611802506987418
|
34 |
+
- name: Recall (macro)
|
35 |
+
type: recall_macro
|
36 |
+
value: 0.6126461527097806
|
37 |
+
- name: F1 (entity span)
|
38 |
+
type: f1_entity_span
|
39 |
+
value: 0.7909735954402699
|
40 |
+
- name: Precision (entity span)
|
41 |
+
type: precision_entity_span
|
42 |
+
value: 0.7956007956007956
|
43 |
+
- name: Recall (entity span)
|
44 |
+
type: recall_entity_span
|
45 |
+
value: 0.7863999074823639
|
46 |
+
- task:
|
47 |
+
name: Token Classification
|
48 |
+
type: token-classification
|
49 |
+
dataset:
|
50 |
+
name: tner/tweetner7/test_2020
|
51 |
+
type: tner/tweetner7/test_2020
|
52 |
+
args: tner/tweetner7/test_2020
|
53 |
+
metrics:
|
54 |
+
- name: F1
|
55 |
+
type: f1
|
56 |
+
value: 0.6516111264114568
|
57 |
+
- name: Precision
|
58 |
+
type: precision
|
59 |
+
value: 0.6942488262910798
|
60 |
+
- name: Recall
|
61 |
+
type: recall
|
62 |
+
value: 0.6139076284379865
|
63 |
+
- name: F1 (macro)
|
64 |
+
type: f1_macro
|
65 |
+
value: 0.6135259272473801
|
66 |
+
- name: Precision (macro)
|
67 |
+
type: precision_macro
|
68 |
+
value: 0.6543224335799225
|
69 |
+
- name: Recall (macro)
|
70 |
+
type: recall_macro
|
71 |
+
value: 0.5830306967374339
|
72 |
+
- name: F1 (entity span)
|
73 |
+
type: f1_entity_span
|
74 |
+
value: 0.7680440771349863
|
75 |
+
- name: Precision (entity span)
|
76 |
+
type: precision_entity_span
|
77 |
+
value: 0.8185554903112156
|
78 |
+
- name: Recall (entity span)
|
79 |
+
type: recall_entity_span
|
80 |
+
value: 0.723404255319149
|
81 |
+
|
82 |
+
pipeline_tag: token-classification
|
83 |
+
widget:
|
84 |
+
- text: "Get the all-analog Classic Vinyl Edition of `Takin' Off` Album from {{@Herbie Hancock@}} via {{USERNAME}} link below: {{URL}}"
|
85 |
+
example_title: "NER Example 1"
|
86 |
+
---
|
87 |
+
# tner/bertweet-base-tweetner7-2020-2021-continuous
|
88 |
+
|
89 |
+
This model is a fine-tuned version of [tner/bertweet-base-tweetner-2020](https://huggingface.co/tner/bertweet-base-tweetner-2020) on the
|
90 |
+
[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`.
|
91 |
+
Model fine-tuning is done via [T-NER](https://github.com/asahi417/tner)'s hyper-parameter search (see the repository
|
92 |
+
for more detail). It achieves the following results on the test set of 2021:
|
93 |
+
- F1 (micro): 0.6584472230299506
|
94 |
+
- Precision (micro): 0.6623376623376623
|
95 |
+
- Recall (micro): 0.6546022201665125
|
96 |
+
- F1 (macro): 0.6102300887168732
|
97 |
+
- Precision (macro): 0.611802506987418
|
98 |
+
- Recall (macro): 0.6126461527097806
|
99 |
+
|
100 |
+
|
101 |
+
|
102 |
+
The per-entity breakdown of the F1 score on the test set are below:
|
103 |
+
- corporation: 0.5185185185185185
|
104 |
+
- creative_work: 0.4682686383240912
|
105 |
+
- event: 0.49658536585365853
|
106 |
+
- group: 0.6117404737384141
|
107 |
+
- location: 0.6658081133290406
|
108 |
+
- person: 0.8447412353923205
|
109 |
+
- product: 0.6659482758620691
|
110 |
+
|
111 |
+
For F1 scores, the confidence interval is obtained by bootstrap as below:
|
112 |
+
- F1 (micro):
|
113 |
+
- 90%: [0.6494608590732527, 0.6679885108746003]
|
114 |
+
- 95%: [0.6476930900555805, 0.6694290853194725]
|
115 |
+
- F1 (macro):
|
116 |
+
- 90%: [0.6494608590732527, 0.6679885108746003]
|
117 |
+
- 95%: [0.6476930900555805, 0.6694290853194725]
|
118 |
+
|
119 |
+
Full evaluation can be found at [metric file of NER](https://huggingface.co/tner/bertweet-base-tweetner7-2020-2021-continuous/raw/main/eval/metric.json)
|
120 |
+
and [metric file of entity span](https://huggingface.co/tner/bertweet-base-tweetner7-2020-2021-continuous/raw/main/eval/metric_span.json).
|
121 |
+
|
122 |
+
### Usage
|
123 |
+
This model can be used through the [tner library](https://github.com/asahi417/tner). Install the library via pip
|
124 |
+
```shell
|
125 |
+
pip install tner
|
126 |
+
```
|
127 |
+
and activate model as below.
|
128 |
+
```python
|
129 |
+
from tner import TransformersNER
|
130 |
+
model = TransformersNER("tner/bertweet-base-tweetner7-2020-2021-continuous")
|
131 |
+
model.predict(["Jacob Collier is a Grammy awarded English artist from London"])
|
132 |
+
```
|
133 |
+
It can be used via transformers library but it is not recommended as CRF layer is not supported at the moment.
|
134 |
+
|
135 |
+
### Training hyperparameters
|
136 |
+
|
137 |
+
The following hyperparameters were used during training:
|
138 |
+
- dataset: ['tner/tweetner7']
|
139 |
+
- dataset_split: train_2021
|
140 |
+
- dataset_name: None
|
141 |
+
- local_dataset: None
|
142 |
+
- model: tner/bertweet-base-tweetner-2020
|
143 |
+
- crf: True
|
144 |
+
- max_length: 128
|
145 |
+
- epoch: 30
|
146 |
+
- batch_size: 32
|
147 |
+
- lr: 1e-05
|
148 |
+
- random_seed: 0
|
149 |
+
- gradient_accumulation_steps: 1
|
150 |
+
- weight_decay: 1e-07
|
151 |
+
- lr_warmup_step_ratio: 0.3
|
152 |
+
- max_grad_norm: 1
|
153 |
+
|
154 |
+
The full configuration can be found at [fine-tuning parameter file](https://huggingface.co/tner/bertweet-base-tweetner7-2020-2021-continuous/raw/main/trainer_config.json).
|
155 |
+
|
156 |
+
### Reference
|
157 |
+
If you use any resource from T-NER, please consider to cite our [paper](https://aclanthology.org/2021.eacl-demos.7/).
|
158 |
+
|
159 |
+
```
|
160 |
+
|
161 |
+
@inproceedings{ushio-camacho-collados-2021-ner,
|
162 |
+
title = "{T}-{NER}: An All-Round Python Library for Transformer-based Named Entity Recognition",
|
163 |
+
author = "Ushio, Asahi and
|
164 |
+
Camacho-Collados, Jose",
|
165 |
+
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
|
166 |
+
month = apr,
|
167 |
+
year = "2021",
|
168 |
+
address = "Online",
|
169 |
+
publisher = "Association for Computational Linguistics",
|
170 |
+
url = "https://aclanthology.org/2021.eacl-demos.7",
|
171 |
+
doi = "10.18653/v1/2021.eacl-demos.7",
|
172 |
+
pages = "53--62",
|
173 |
+
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.",
|
174 |
+
}
|
175 |
+
|
176 |
+
```
|
eval/metric.test_2020.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"micro/f1": 0.6516111264114568, "micro/f1_ci": {"90": [0.6307643696766942, 0.6719969183970778], "95": [0.6279769593276863, 0.6754876660511644]}, "micro/recall": 0.6139076284379865, "micro/precision": 0.6942488262910798, "macro/f1": 0.6135259272473801, "macro/f1_ci": {"90": [0.5906927661860492, 0.6344368144341196], "95": [0.5857025826391625, 0.6398643336684641]}, "macro/recall": 0.5830306967374339, "macro/precision": 0.6543224335799225, "per_entity_metric": {"corporation": {"f1": 0.5576407506702413, "f1_ci": {"90": [0.49716845518670816, 0.6133509933774834], "95": [0.4834629553827261, 0.6226928728295388]}, "precision": 0.5714285714285714, "recall": 0.5445026178010471}, "creative_work": {"f1": 0.5683060109289618, "f1_ci": {"90": [0.5116146934460888, 0.6213143806261214], "95": [0.4987511327781342, 0.6269530761644141]}, "precision": 0.5561497326203209, "recall": 0.5810055865921788}, "event": {"f1": 0.4621513944223108, "f1_ci": {"90": [0.407666973744818, 0.5147216611966674], "95": [0.39747293617586504, 0.5267074887252602]}, "precision": 0.48945147679324896, "recall": 0.4377358490566038}, "group": {"f1": 0.5632183908045978, "f1_ci": {"90": [0.5081111741349972, 0.6198251387919285], "95": [0.4973684935701162, 0.627101507914578]}, "precision": 0.6966824644549763, "recall": 0.47266881028938906}, "location": {"f1": 0.6626865671641792, "f1_ci": {"90": [0.5987634662263112, 0.7208521653381543], "95": [0.5852242504835591, 0.7327961432506889]}, "precision": 0.6529411764705882, "recall": 0.6727272727272727}, "person": {"f1": 0.8293963254593175, "f1_ci": {"90": [0.80330438414185, 0.8518550780745903], "95": [0.7989825274493244, 0.8552756712441073]}, "precision": 0.8665447897623401, "recall": 0.7953020134228188}, "product": {"f1": 0.6512820512820514, "f1_ci": {"90": [0.6014985014985015, 0.7033119235335301], "95": [0.5895308160048044, 0.7101524983776768]}, "precision": 0.7470588235294118, "recall": 0.5772727272727273}}}
|
eval/{metric.json → metric.test_2021.json}
RENAMED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"micro/f1": 0.6584472230299506, "micro/f1_ci": {"90": [0.6494608590732527, 0.6679885108746003], "95": [0.6476930900555805, 0.6694290853194725]}, "micro/recall": 0.6546022201665125, "micro/precision": 0.6623376623376623, "macro/f1": 0.6102300887168732, "macro/f1_ci": {"90": [0.6004038513370128, 0.6197560648878369], "95": [0.5983376336540169, 0.6210193530268486]}, "macro/recall": 0.6126461527097806, "macro/precision": 0.611802506987418, "per_entity_metric": {"corporation": {"f1": 0.5185185185185185, "f1_ci": {"90": [0.49337153061983774, 0.5439587858969501], "95": [0.48740574277388654, 0.5496106513391685]}, "precision": 0.5159515951595159, "recall": 0.5211111111111111}, "creative_work": {"f1": 0.4682686383240912, "f1_ci": {"90": [0.438666115261993, 0.4978700091388796], "95": [0.43393763344195974, 0.503641894873691]}, "precision": 0.4260089686098655, "recall": 0.5198358413132695}, "event": {"f1": 0.49658536585365853, "f1_ci": {"90": [0.47272381446418543, 0.5189233272281362], "95": [0.46833006812245065, 0.52501206086096]}, "precision": 0.5352260778128286, "recall": 0.46314831665150136}, "group": {"f1": 0.6117404737384141, "f1_ci": {"90": [0.591561073989307, 0.6339137710303029], "95": [0.5878883127243717, 0.63736429288823]}, "precision": 0.6387096774193548, "recall": 0.5869565217391305}, "location": {"f1": 0.6658081133290406, "f1_ci": {"90": [0.6385166723863426, 0.692362621847589], "95": [0.6316389021787584, 0.6965855246144679]}, "precision": 0.6176821983273596, "recall": 0.7220670391061452}, "person": {"f1": 0.8447412353923205, "f1_ci": {"90": [0.8347663259120971, 0.8552561479552422], "95": [0.8329609550207723, 0.8566901985328257]}, "precision": 0.8499440089585666, "recall": 0.8396017699115044}, "product": {"f1": 0.6659482758620691, "f1_ci": {"90": [0.6434850321173191, 0.6866341444247477], "95": [0.6403631144443871, 0.690716861020364]}, "precision": 0.6990950226244343, "recall": 0.6358024691358025}}}
|
eval/metric_span.test_2020.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"micro/f1": 0.7680440771349863, "micro/f1_ci": {}, "micro/recall": 0.723404255319149, "micro/precision": 0.8185554903112156, "macro/f1": 0.7680440771349863, "macro/f1_ci": {}, "macro/recall": 0.723404255319149, "macro/precision": 0.8185554903112156}
|
eval/metric_span.test_2021.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"micro/f1": 0.7909735954402699, "micro/f1_ci": {}, "micro/recall": 0.7863999074823639, "micro/precision": 0.7956007956007956, "macro/f1": 0.7909735954402699, "macro/f1_ci": {}, "macro/recall": 0.7863999074823639, "macro/precision": 0.7956007956007956}
|
eval/prediction.2020.test.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
eval/prediction.2021.dev.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
eval/prediction.2021.test.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
trainer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"dataset": ["tner/tweetner7"], "dataset_split": "train_2021", "dataset_name": null, "local_dataset": null, "model": "tner/bertweet-base-tweetner-2020", "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}
|