Recent Updates
- Feb 8, 2022 Please check out this page for information on paper submission.
- Feb 5, 2022 Rankings are out.
- Jan 25, 2022 Test phase duration is increased by 2 days. New end date Jan 30 23:59 UTC.
- Jan 04, 2022 FAQs about test phase are answered.
- Oct 28, 2021 Submission site on Codalab is open now. Register now!
- Oct 25, 2021 Updated information on participation and preparing submissions.
- Sep 10, 2021 A Baseline system with dev set results is available.
- Join us in Slack.
- Sep 03, 2021 Training data is available.
- Aug 23, 2021 Competition page has some trial data.
Important Dates
Trial Data Ready |
|
Training Data Ready |
|
Evaluation Start |
|
Evaluation End |
|
System Description Paper Submission Due |
|
Notification to Authors |
|
Camera-ready Due | Apr 21 (Thu), 2022 |
Workshop | 14-15 July 2022 co-located with NAACL |
Baseline System
We have released a baseline system that fine-tunes the XLM-RoBERTa base model for each of the dataset.
This code repository provides the baseline approach for Named Entity Recognition (NER). In this repository the following functionalities are provided:
- CoNLL data readers
- Usage of any HuggingFace pre-trained transformer models
- Training and Testing through Pytorch-Lightning
We expect, this baseline can be the starting point from where the participants can start building their own systems.
Baselines Results
For the baseline model performance in the development set, please check the Codalab leaderboard. Baseline submissions are made with the team name “MultiCoNER Baseline”.
Results on test set
Track | Macro F1 |
---|---|
English | 0.612 |
German | 0.634 |
Spanish | 0.574 |
Russian | 0.591 |
Dutch | 0.616 |
Korean | 0.546 |
Farsi | 0.518 |
Turkish | 0.457 |
Chinese | 0.511 |
Hindi | 0.469 |
Bangla | 0.391 |
Multi | 0.541 |
Mix | 0.581 |
Communication
-
Join us in Slack
-
Subscribe to the task mailing list