Recent Updates


  • Feb 20, 2023 Papers should be submitted here
  • Feb 7, 2023 Please check out this page for information on paper submission.
  • Feb 7, 2023 Rankings are out.
  • Jan 25, 2023 Evaluation phase is extended by 24 hours. This phase will end on February 1st 11:59 pm AOE.
  • Jan 25, 2023 Evaluation phase site with test data is available in Codalab.
  • Jan 18, 2023 Practice phase site on Codalab is open now.

Important Dates

* All deadlines are calculated at 11:59 pm
UTC-12 hours

Trial Data Ready Jul 15 (Fri), 2022
Training Data Ready Sep 30 (Fri), 2022
Evaluation Start Jan 25 (Wed), 2023
Evaluation End Feb 1 (Wed), 2023
System Description Paper Submission Due Feb 28 (Tue), 2023
Notification to Authors Mar 31 (Fri), 2023
Camera-ready Due Apr 21 (Fri), 2023
Workshop 13-14 July 2023 co-located with ACL

The dataset is publicly available here.

You can download the data using the following command:

aws s3 cp --no-sign-request s3://multiconer/multiconer2023/ multiconer2023/ --recursive

Tagset

The tagset of MultiCoNER is a fine-grained tagset.

The fine to coarse level mapping of the tags are as follows:

The following figure shows the fine-grained taxonomy of the dataset. Taxonomy

Here are some examples from the dataset.

* Bangla: [লিটল মিক্স | MusicalGrp] এ যোগদানের আগে তিনি [পিৎজা হাট | ORG] এ ওয়েট্রেস হিসাবে কাজ করেছিলেন।
* Chinese: 它的纤维穿过 [锁骨 | AnatomicalStructure] 并沿颈部侧面倾斜向上和内侧.
* English: [wes anderson | Artist]'s film [the grand budapest hotel | VisualWork] opened the festival .
* Farsi:     است] ناگویا |HumanSettlement] مرکزاین استان شهر
* French: l [amiral de coligny | Politician] réussit à s y glisser .
* German: in [frühgeborenes | Disease] führt dies zu [irds | Symptom] .
* Hindi: १७९६ में उन्हें [शाही स्वीडिश विज्ञान अकादमी | Facility] का सदस्य चुना गया।
* Italian: è conservato nel [rijksmuseum | Facility] di [amsterdam | HumanSettlement] .
* Portuguese: também é utilizado para se fazer [licor | Drink] e [vinhos | Drink].
* Spanish: fue superado por el [aon center | Facility] de [los ángeles | HumanSettlement] .
* Swedish: [tom hamilton | Artist] amerikansk musiker basist i [aerosmith | MusicalGRP] .
* Ukrainian: назва альбому походить з роману « [кінець дитинства | WrittenWork] » англійського письменника [артура кларка | Artist] .

Data Statistics

Language Training Validataion Test
BN-Bangla 9,708 507 19,859
DE-German 9,785 512 20,145
EN-English 16,778 871 249,980
ES-Spanish 16,453 854 246,900
FA-Farsi 16,321 855 219,168
FR-French 16,548 857 249,786
HI-Hindi 9,632 514 18,399
IT-Italian 16,579 858 247,881
PT-Portuguese 16,469 854 229,490
SV-Swedish 16,363 856 231,190
UK-Ukrainian 16,429 851 238,296
ZH-Chinese 9,759 506 20,265
MULTI-Multilingual 170,824 8,895 358,668

Communication