Librarian Bot: Add base_model information to model

1d6631d 10 months ago

8.29 kB

	---
	datasets:
	- tner/tweetner7
	metrics:
	- f1
	- precision
	- recall
	pipeline_tag: token-classification
	widget:
	- text: 'Get the all-analog Classic Vinyl Edition of `Takin'' Off` Album from {@herbiehancock@}
	via {@bluenoterecords@} link below: {{URL}}'
	example_title: NER Example 1
	base_model: cardiffnlp/twitter-roberta-base-dec2021
	model-index:
	- name: tner/twitter-roberta-base-dec2021-tweetner7-2021
	results:
	- task:
	type: token-classification
	name: Token Classification
	dataset:
	name: tner/tweetner7
	type: tner/tweetner7
	args: tner/tweetner7
	metrics:
	- type: f1
	value: 0.6346897022050466
	name: F1 (test_2021)
	- type: precision
	value: 0.6240500670540903
	name: Precision (test_2021)
	- type: recall
	value: 0.6456984273820536
	name: Recall (test_2021)
	- type: f1_macro
	value: 0.586830362928695
	name: Macro F1 (test_2021)
	- type: precision_macro
	value: 0.5777962671668668
	name: Macro Precision (test_2021)
	- type: recall_macro
	value: 0.5983908809408913
	name: Macro Recall (test_2021)
	- type: f1_entity_span
	value: 0.77487922705314
	name: Entity Span F1 (test_2021)
	- type: precision_entity_span
	value: 0.7618462226195798
	name: Entity Span Precision (test_2020)
	- type: recall_entity_span
	value: 0.7883659072510697
	name: Entity Span Recall (test_2021)
	- type: f1
	value: 0.6225596529284164
	name: F1 (test_2020)
	- type: precision
	value: 0.6519023282226007
	name: Precision (test_2020)
	- type: recall
	value: 0.5957446808510638
	name: Recall (test_2020)
	- type: f1_macro
	value: 0.578847416026638
	name: Macro F1 (test_2020)
	- type: precision_macro
	value: 0.6085991227224318
	name: Macro Precision (test_2020)
	- type: recall_macro
	value: 0.5537596756202443
	name: Macro Recall (test_2020)
	- type: f1_entity_span
	value: 0.7413232104121477
	name: Entity Span F1 (test_2020)
	- type: precision_entity_span
	value: 0.7762634866553095
	name: Entity Span Precision (test_2020)
	- type: recall_entity_span
	value: 0.7093928386092372
	name: Entity Span Recall (test_2020)
	---
	# tner/twitter-roberta-base-dec2021-tweetner7-2021

	This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-dec2021](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2021) on the
	[tner/tweetner7](https://huggingface.co/datasets/tner/tweetner7) dataset (`train_2021` 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): 0.6346897022050466
	- Precision (micro): 0.6240500670540903
	- Recall (micro): 0.6456984273820536
	- F1 (macro): 0.586830362928695
	- Precision (macro): 0.5777962671668668
	- Recall (macro): 0.5983908809408913



	The per-entity breakdown of the F1 score on the test set are below:
	- corporation: 0.47679083094555874
	- creative_work: 0.4394942805538832
	- event: 0.4638082065467958
	- group: 0.5936801787424194
	- location: 0.646505376344086
	- person: 0.8201674554058972
	- product: 0.6673662119622246

	For F1 scores, the confidence interval is obtained by bootstrap as below:
	- F1 (micro):
	- 90%: [0.6258493958055198, 0.6436753593746133]
	- 95%: [0.6239476803844971, 0.645859449522042]
	- F1 (macro):
	- 90%: [0.6258493958055198, 0.6436753593746133]
	- 95%: [0.6239476803844971, 0.645859449522042]

	Full evaluation can be found at [metric file of NER](https://huggingface.co/tner/twitter-roberta-base-dec2021-tweetner7-2021/raw/main/eval/metric.json)
	and [metric file of entity span](https://huggingface.co/tner/twitter-roberta-base-dec2021-tweetner7-2021/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
	```
	[TweetNER7](https://huggingface.co/datasets/tner/tweetner7) pre-processed tweets where the account name and URLs are
	converted into special formats (see the dataset page for more detail), so we process tweets accordingly and then run the model prediction as below.

	```python
	import re
	from urlextract import URLExtract
	from tner import TransformersNER

	extractor = URLExtract()

	def format_tweet(tweet):
	# mask web urls
	urls = extractor.find_urls(tweet)
	for url in urls:
	tweet = tweet.replace(url, "{{URL}}")
	# format twitter account
	tweet = re.sub(r"\b(\s*)(@[\S]+)\b", r'\1{\2@}', tweet)
	return tweet


	text = "Get the all-analog Classic Vinyl Edition of `Takin' Off` Album from @herbiehancock via @bluenoterecords link below: http://bluenote.lnk.to/AlbumOfTheWeek"
	text_format = format_tweet(text)
	model = TransformersNER("tner/twitter-roberta-base-dec2021-tweetner7-2021")
	model.predict([text_format])
	```
	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_2021
	- dataset_name: None
	- local_dataset: None
	- model: cardiffnlp/twitter-roberta-base-dec2021
	- 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: 0.15
	- max_grad_norm: 1

	The full configuration can be found at [fine-tuning parameter file](https://huggingface.co/tner/twitter-roberta-base-dec2021-tweetner7-2021/raw/main/trainer_config.json).

	### Reference
	If you use the model, please cite T-NER paper and TweetNER7 paper.
	- T-NER
	```

	@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.",
	}

	```
	- TweetNER7
	```

	@inproceedings{ushio-etal-2022-tweet,
	title = "{N}amed {E}ntity {R}ecognition in {T}witter: {A} {D}ataset and {A}nalysis on {S}hort-{T}erm {T}emporal {S}hifts",
	author = "Ushio, Asahi and
	Neves, Leonardo and
	Silva, Vitor and
	Barbieri, Francesco. and
	Camacho-Collados, Jose",
	booktitle = "The 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing",
	month = nov,
	year = "2022",
	address = "Online",
	publisher = "Association for Computational Linguistics",
	}

	```