asahi417's picture
model update
- tner/conll2003
- f1
- precision
- recall
- name: tner/roberta-large-conll2003
- task:
name: Token Classification
type: token-classification
name: tner/conll2003
type: tner/conll2003
args: tner/conll2003
- name: F1
type: f1
value: 0.924769027716674
- name: Precision
type: precision
value: 0.9191883855168795
- name: Recall
type: recall
value: 0.9304178470254958
- name: F1 (macro)
type: f1_macro
value: 0.9110950780089749
- name: Precision (macro)
type: precision_macro
value: 0.9030546238754271
- name: Recall (macro)
type: recall_macro
value: 0.9197126371122274
- name: F1 (entity span)
type: f1_entity_span
value: 0.9619852164730729
- name: Precision (entity span)
type: precision_entity_span
value: 0.9562631210636809
- name: Recall (entity span)
type: recall_entity_span
value: 0.9677762039660056
pipeline_tag: token-classification
- text: "Jacob Collier is a Grammy awarded artist from England."
example_title: "NER Example 1"
# tner/roberta-large-conll2003
This model is a fine-tuned version of [roberta-large]( on the
[tner/conll2003]( 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): 0.924769027716674
- Precision (micro): 0.9191883855168795
- Recall (micro): 0.9304178470254958
- F1 (macro): 0.9110950780089749
- Precision (macro): 0.9030546238754271
- Recall (macro): 0.9197126371122274
The per-entity breakdown of the F1 score on the test set are below:
- location: 0.9390573401380967
- organization: 0.9107142857142857
- other: 0.8247422680412372
- person: 0.9698664181422801
For F1 scores, the confidence interval is obtained by bootstrap as below:
- F1 (micro):
- 90%: [0.9185189408755685, 0.9309806929048586]
- 95%: [0.9174010190551032, 0.9318590917100465]
- F1 (macro):
- 90%: [0.9185189408755685, 0.9309806929048586]
- 95%: [0.9174010190551032, 0.9318590917100465]
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-conll2003")
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/conll2003']
- dataset_split: train
- dataset_name: None
- local_dataset: None
- model: roberta-large
- crf: True
- max_length: 128
- epoch: 17
- 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](
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 = "",
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.",