metadata
datasets:
- tner/tweebank_ner
metrics:
- f1
- precision
- recall
pipeline_tag: token-classification
widget:
- text: Jacob Collier is a Grammy awarded artist from England.
example_title: NER Example 1
base_model: roberta-large
model-index:
- name: tner/roberta-large-tweebank-ner
results:
- task:
type: token-classification
name: Token Classification
dataset:
name: tner/tweebank_ner
type: tner/tweebank_ner
args: tner/tweebank_ner
metrics:
- type: f1
value: 0.7439490445859872
name: F1
- type: precision
value: 0.7121951219512195
name: Precision
- type: recall
value: 0.7786666666666666
name: Recall
- type: f1_macro
value: 0.7354319457314183
name: F1 (macro)
- type: precision_macro
value: 0.712928566565599
name: Precision (macro)
- type: recall_macro
value: 0.7620465365030582
name: Recall (macro)
- type: f1_entity_span
value: 0.8178343949044585
name: F1 (entity span)
- type: precision_entity_span
value: 0.7829268292682927
name: Precision (entity span)
- type: recall_entity_span
value: 0.856
name: Recall (entity span)
tner/roberta-large-tweebank-ner
This model is a fine-tuned version of roberta-large on the tner/tweebank_ner dataset. Model fine-tuning is done via T-NER's hyper-parameter search (see the repository for more detail). It achieves the following results on the test set:
- F1 (micro): 0.7439490445859872
- Precision (micro): 0.7121951219512195
- Recall (micro): 0.7786666666666666
- F1 (macro): 0.7354319457314183
- Precision (macro): 0.712928566565599
- Recall (macro): 0.7620465365030582
The per-entity breakdown of the F1 score on the test set are below:
- location: 0.7782805429864253
- organization: 0.7377049180327869
- other: 0.5520581113801453
- person: 0.8736842105263157
For F1 scores, the confidence interval is obtained by bootstrap as below:
- F1 (micro):
- 90%: [0.7156413818791614, 0.771698046498159]
- 95%: [0.7063867669973017, 0.7763088810979543]
- F1 (macro):
- 90%: [0.7156413818791614, 0.771698046498159]
- 95%: [0.7063867669973017, 0.7763088810979543]
Full evaluation can be found at metric file of NER and metric file of entity span.
Usage
This model can be used through the tner library. Install the library via pip
pip install tner
and activate model as below.
from tner import TransformersNER
model = TransformersNER("tner/roberta-large-tweebank-ner")
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/tweebank_ner']
- dataset_split: train
- dataset_name: None
- local_dataset: None
- model: roberta-large
- crf: True
- max_length: 128
- epoch: 15
- batch_size: 64
- lr: 1e-05
- random_seed: 42
- gradient_accumulation_steps: 1
- weight_decay: None
- lr_warmup_step_ratio: 0.1
- max_grad_norm: 10.0
The full configuration can be found at fine-tuning parameter file.
Reference
If you use any resource from T-NER, please consider to cite our paper.
@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.",
}