README.md

---
license: apache-2.0
language: en
datasets:
- Jzuluaga/atco2_corpus_1h
tags:
- text
- token-classification
- en-atc
- en
- generated_from_trainer
- bert
- ner-for-atc
metrics:
- Precision
- Recall
- Accuracy
- F1
widget:
- text: "lining up runway three one csa five bravo easy five three kilo romeo contact ruzyne ground one two one decimal nine good bye"
- text: "csa seven three two zero so change of taxi quality eight nine sierra we need to full length britair five nine zero bravo contact ruzyne ground one two one decimal nine good bye"
- text: "swiss four six one foxtrot line up runway three one and wait one two one nine csa four yankee alfa"
- text: "tower klm five five tango ils three one wizz air four papa uniform tower roger"
model-index:
- name: bert-base-ner-atc-en-atco2-1h
  results:
  - task:
        type: token-classification
        name: ner
    dataset:
        type: Jzuluaga/atco2_corpus_1h
        name: ATCO2 corpus (Air Traffic Control Communications)
        config: test
        split: test
    metrics:
    - type: F1
      value: 0.94
      name: TEST F1 (callsign)
      verified: False
    - type: F1
      value: 0.74
      name: TEST F1 (command)
      verified: False
    - type: F1
      value: 0.81
      name: TEST F1 (value)
      verified: False     
---

# bert-base-ner-atc-en-atco2-1h

This model allow to perform named-entity recognition (NER) on air traffic control communications data. We solve this challenge by performing token classification (NER) with a BERT model. 
We fine-tune a pretrained BERT model on the ner task. 

For instance, if you have the following transcripts/gold annotations:

- **Utterance**: lufthansa three two five cleared to land runway three four left

Could you tell what are the main entities in the communication? The desired output is shown below:

- **Named-entity module output**: [call] lufthansa three two five [/call] [cmd] cleared to land [/cmd] [val] runway three four left [/val]

This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co./bert-base-uncased) on the [atco2_corpus_1h](https://huggingface.co./datasets/Jzuluaga/atco2_corpus_1h). 

<a href="https://github.com/idiap/atco2-corpus">
    <img alt="GitHub" src="https://img.shields.io/badge/GitHub-Open%20source-green\">
</a>

It achieves the following results on the development set:
- Loss: 1.4282
- Precision: 0.6195
- Recall: 0.7071
- F1: 0.6604
- Accuracy: 0.8182

**Paper**: [ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications](https://arxiv.org/abs/2211.04054)

Authors: Juan Zuluaga-Gomez, Karel Veselý, Igor Szöke, Petr Motlicek, Martin Kocour, Mickael Rigault, Khalid Choukri, Amrutha Prasad and others

Abstract: Personal assistants, automatic speech recognizers and dialogue understanding systems are becoming more critical in our interconnected digital world. A clear example is air traffic control (ATC) communications. ATC aims at guiding aircraft and controlling the airspace in a safe and optimal manner. These voice-based dialogues are carried between an air traffic controller (ATCO) and pilots via very-high frequency radio channels. In order to incorporate these novel technologies into ATC (low-resource domain), large-scale annotated datasets are required to develop the data-driven AI systems. Two examples are automatic speech recognition (ASR) and natural language understanding (NLU). In this paper, we introduce the ATCO2 corpus, a dataset that aims at fostering research on the challenging ATC field, which has lagged behind due to lack of annotated data. The ATCO2 corpus covers 1) data collection and pre-processing, 2) pseudo-annotations of speech data, and 3) extraction of ATC-related named entities. The ATCO2 corpus is split into three subsets. 1) ATCO2-test-set corpus contains 4 hours of ATC speech with manual transcripts and a subset with gold annotations for named-entity recognition (callsign, command, value). 2) The ATCO2-PL-set corpus consists of 5281 hours of unlabeled ATC data enriched with automatic transcripts from an in-domain speech recognizer, contextual information, speaker turn information, signal-to-noise ratio estimate and English language detection score per sample. Both available for purchase through ELDA at this http URL. 3) The ATCO2-test-set-1h corpus is a one-hour subset from the original test set corpus, that we are offering for free at this https URL. We expect the ATCO2 corpus will foster research on robust ASR and NLU not only in the field of ATC communications but also in the general research community. 

Code — GitHub repository: https://github.com/idiap/atco2-corpus

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 3000

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 125.0 | 500  | 0.8692          | 0.6396    | 0.7172 | 0.6762 | 0.8307   |
| 0.2158        | 250.0 | 1000 | 1.0074          | 0.5702    | 0.6970 | 0.6273 | 0.8245   |
| 0.2158        | 375.0 | 1500 | 1.3560          | 0.6577    | 0.7374 | 0.6952 | 0.8119   |
| 0.0184        | 500.0 | 2000 | 1.3393          | 0.6182    | 0.6869 | 0.6507 | 0.8056   |
| 0.0184        | 625.0 | 2500 | 1.3528          | 0.6087    | 0.7071 | 0.6542 | 0.8213   |
| 0.0175        | 750.0 | 3000 | 1.4282          | 0.6195    | 0.7071 | 0.6604 | 0.8182   |


### Framework versions

- Transformers 4.24.0
- Pytorch 1.13.0+cu117
- Datasets 2.7.0
- Tokenizers 0.13.2