Workshop on NER for South and South East Asian Languages

January 12, 2008, IIIT, Hyderabad, India

Call for Papers
Shared Task
Annotation Guidelines
Accepted Papers
Invited Talks
Workshop Programs
Program Committee
Draft Papers


Submission is now closed.

The hard copy of the Copyright Transfer Form can be sent to the following address:

Anil Kumar Singh

Note: In case of any problem with submission through the site, please just send the paper and the details to anil@research.iiit.ac.in

Paper submission is through the centralized workshop submission page. Papers have to be written in English. Note that shared task contestants also have to submit a paper describing their method and the results etc. Regular papers can be up to 8 pages long, while the maximum length for short papers is 5 pages (including references, figures, tables etc.).

The papers should be formatted using the LaTeX styles or MS Word templates recommended for the main IJCNLP conference. These documents are available here. Reviewing will be blind. The draft papers should not contain any information that can identify the authors, as far as possible.

Authors are encouraged to study this review form for guidance.

Dual Submission Policy

Dual submission is allowed, provided that:

  1. You mention on the first page (below the title) where the paper has been dually submitted.
  2. You let us know as soon as possible if and when you want to withdraw your paper. (You will have to withdraw it from one place if it gets selected in both the places.)

If you have already submitted, you can revise your submission accordingly.

Submission of Results for the Shared Task

Submission of results for the shared task is now closed.

Submission of results for the shared task will be open till 01:29 pm on September 16 17 (IST) or 11:59 pm September 15 16 (PST). This gives the contestants around 48 64 hours to run their system and submit the results. At the end of this period, annotated test data will be uploaded, after which no submission (of shared task results) will be accepted. Note that you actually have to submit annotated data in correct SSF format as explained below:

To submit the data annotated by the NER systems, please follow the steps given below:

  1. Go to the submission page.
  2. Make a new submission, unless you have already made one for the same paper. Otherwise, revise the submission by entering your passcode. You can, however make more than one submission if you plan to submit more than one paper.
  3. Fill in the details. In case you have not finalized anything, you can just fill in something and revise everything (title, abstract etc.) later when you make the paper submission. Then upload the results (a compressed tar file or a zip file) as additional attachment. The output of your NER system for all five languages should be submitted as one tar or zip file. Please note that actual data is to be submitted, not just performance details.

Caution: Please make sure that results are in the same format as the original training data, i.e. SSF format. The total number and order of sentences in the results should remain the same as in the given test data, even if the sentences are wrongly split. Not ensuring this may cause the evaluation script to output wrong values for precision, recall and F-measure. (Node id's in the first column of the SSF format are not important: they just need to be some integer, say 1. All can be 1).

Locations of visitors to this page