[Corpora-List] Ready for the eHealth-KD 2020: eHealth Knowledge Discovery?

Yoan Gutiérrez ygutierrez at dlsi.ua.es
Tue Feb 25 14:56:55 CET 2020


Please consider contributing and/or forwarding to appropriate

colleagues and groups.

****We apologize for the multiple copies of this e-mail******

----------------------------------------------------------------------------------------------------------------------------- First Call for Participation ---TRAINING DATA AVAILABLE--- ---------------------------------------------------------------------------------------------------------------------------- *eHealth-KD 2020: eHealth Knowledge Discovery*

*Webpage*: https://knowledge-learning.github.io/ehealthkd-2020/

*Competition environment link:*TO BE ANNOUNCED

*Datasets and tools:*https://github.com/knowledge-learning/ehealthkd-2020/tree/master/data

/Held as part of the evaluation forum IberLEF in the XXXVI edition of the International Conference of the Spanish Society for Natural Language Processing (SEPLN 2020). September 22-25, 2020. Málaga, Spain./

*/Novelties/*/: This edition will involve an additional scenario in which an alternative domain (not health related) will be evaluated, to experience with *transfer learning techniques*./

eHealth-KD 2020 challenge, as part of the IberLEF 2020 Workshop, proposes in its third edition modelling the human language in a scenario in which electronic health documents could be machine readable from a semantic point of view. With this task, it is expected to encourage the development of software technologies to automatically extract a large variety of knowledge from electronic Health documents written in the *Spanish Language*.

 This involves two subtasks:

1. Entity recognition

<https://knowledge-learning.github.io/ehealthkd-2020/tasks#subtask-a-entity-recognition>

2. Relation extraction

<https://knowledge-learning.github.io/ehealthkd-2020/tasks#subtask-b-relation-extraction>

The challenge will be managed and played by means of the Codalab

Competitions platform. In addition, the Organization Committee of

eHealth-KD encourages participants to submit a description paper of

their systems. Submitted papers will be reviewed by a scientific

committee, and only accepted papers will be *published at CEUR*. The

proceedings of eHealth-KD will be jointly published with the

proceedings of all the tasks of IberLEF 2020. The submitted *papers*

will be *peer-reviewed* by a Program Committee which is composed by

all the participants in the task eHealth-KD and the Organization

Committee.

We encourage the entire research community and especially those

groups working in *knowledge discovery* and *transfer

learning* technologies to participate in this task. If you are

interested in participating, please browse the following link

https://knowledge-learning.github.io/ehealthkd-2020/.

---------------------------------------------------------------------

HOW TO PARTICIPATE

---------------------------------------------------------------------

1. *Join the Google Group* for the task:

_https://groups.google.com/forum/#!forum/ehealth-kd_

2. *Download the datasets*, examples, scoring scripts and baselines

(if needed) from:

https://github.com/knowledge-learning/ehealthkd-2020/tree/master/data and

fill the following form: https://forms.gle/pUJutSDq2FYLwNWQA

3. *TRAIN your system (ACTIVE)*: Train your models and evaluate your

approach by using the evaluation scripts provided at:

https://github.com/knowledge-learning/ehealthkd-2020

4. *Register at: *TO BE ANNOUNCED

5.*   TEST your system*: Submit your results on the test sets at: TO

BE ANNOUNCED

6. *Submit your working notes*. More details in

https://knowledge-learning.github.io/ehealthkd-2020/#Publication%20instructions

7. *Come to Málaga//*/September 22, 2020 /to attend the discussion

of the results of IberLEF evaluation campaigns at a workshop

collocated with SEPLN 2020.

/Lets do it!/

-------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 30070 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20200225/69652efb/attachment.txt>



More information about the Corpora mailing list