model update

4ec2d4b 11 months ago

No virus

5.73 kB

	---
	datasets:
	- tner/tweetner7
	metrics:
	- f1
	- precision
	- recall
	model-index:
	- name: cardiffnlp/twitter-roberta-base-2022-154m-tweetner7-2020
	results:
	- task:
	name: Token Classification
	type: token-classification
	dataset:
	name: tner/tweetner7
	type: tner/tweetner7
	args: tner/tweetner7
	metrics:
	- name: F1
	type: f1
	value: 0.6419150543257219
	- name: Precision
	type: precision
	value: 0.6451010159990658
	- name: Recall
	type: recall
	value: 0.6387604070305273
	- name: F1 (macro)
	type: f1_macro
	value: 0.5829431071584856
	- name: Precision (macro)
	type: precision_macro
	value: 0.5886989381701707
	- name: Recall (macro)
	type: recall_macro
	value: 0.5796110916728531
	- name: F1 (entity span)
	type: f1_entity_span
	value: 0.7753631609529343
	- name: Precision (entity span)
	type: precision_entity_span
	value: 0.7791661800770758
	- name: Recall (entity span)
	type: recall_entity_span
	value: 0.7715970856944605

	pipeline_tag: token-classification
	widget:
	- text: "Jacob Collier is a Grammy awarded artist from England."
	example_title: "NER Example 1"
	---
	# cardiffnlp/twitter-roberta-base-2022-154m-tweetner7-2020

	This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-2022-154m](https://huggingface.co/cardiffnlp/twitter-roberta-base-2022-154m) on the
	[tner/tweetner7](https://huggingface.co/datasets/tner/tweetner7) dataset.
	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:
	- F1 (micro): 0.6419150543257219
	- Precision (micro): 0.6451010159990658
	- Recall (micro): 0.6387604070305273
	- F1 (macro): 0.5829431071584856
	- Precision (macro): 0.5886989381701707
	- Recall (macro): 0.5796110916728531

	The per-entity breakdown of the F1 score on the test set are below:
	- corporation: 0.5127020785219399
	- event: 0.43384759233286585
	- group: 0.6000666000666002
	- location: 0.6535326086956522
	- person: 0.8390577234310376
	- product: 0.6386386386386387
	- work_of_art: 0.40275650842266464

	For F1 scores, the confidence interval is obtained by bootstrap as below:
	- F1 (micro):

	- F1 (macro):


	Full evaluation can be found at [metric file of NER](https://huggingface.co/cardiffnlp/twitter-roberta-base-2022-154m-tweetner7-2020/raw/main/eval/metric.json)
	and [metric file of entity span](https://huggingface.co/cardiffnlp/twitter-roberta-base-2022-154m-tweetner7-2020/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("cardiffnlp/twitter-roberta-base-2022-154m-tweetner7-2020")
	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_2020
	- dataset_name: None
	- local_dataset: None
	- model: cardiffnlp/twitter-roberta-base-2022-154m
	- crf: True
	- max_length: 128
	- epoch: 30
	- batch_size: 32
	- lr: 0.0001
	- random_seed: 42
	- gradient_accumulation_steps: 1
	- weight_decay: 1e-07
	- lr_warmup_step_ratio: 0.3
	- max_grad_norm: 10

	The full configuration can be found at [fine-tuning parameter file](https://huggingface.co/cardiffnlp/twitter-roberta-base-2022-154m-tweetner7-2020/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.",
	}

	```