Chemotherapy Treatment Timelines Extraction
from the Clinical Narrative:
Submission of Papers
Chemotherapy Treatment Timelines Extraction
from the Clinical Narrative:
Submission of Papers
Participants will be invited to submit papers describing their systems.
Proceedings will be published in the ACL Anthology under the upcoming ACL Special Interest Group on Clinically Related Language (SIGClinical).
The OpenReview submission system is ready: https://openreview.net/group?id=clinical-nlp.github.io/Clinical_NLP/2025/Workshop#tab-recent-activity
Also see https://clinical-nlp.github.io/2025/call-for-papers.html
The paper submission guidelines are similar to last year:
(a) Papers may have up to eight (8) pages of content.
(b) Unlimited pages for references. Any “Limitations” section or “Ethics Statement” is similar to references; it does not count toward the page limit
(c) Submissions should be anonymous and must not include any identifying information about the authors: https://acl-org.github.io/ACLPUB/review-version.html
(d) ACL formatting guidelines: https://acl-org.github.io/ACLPUB/formatting.html
(e) If relevant, these are the MEDIQA 2025 paper submission guidelines: https://sites.google.com/view/mediqa-2025/paper-guidelines
Participants will be invited to submit papers describing their systems.
Submission and camera-ready paper requirements:
The format is the ACL format, a short paper (4 pages), and a long paper (8 pages). You can submit a paper even if you participated in only one subtask. ACL paper template
(for submissions only, not for camera-ready papers) Submissions should be anonymous and must not include any identifying information about the authors
Long papers may have up to eight (8) pages of content and short papers may have up to four (4) pages of content.
You are allowed unlimited pages for references
Any “Limitations” section or “Ethics Statement” is similar to references; it does not count toward the page limit.
Please, do not describe the task, it is described in the overview paper for the shared task. Please, cite:
*Jiarui Yao, *Harry Hochheiser, WonJin Yoon, Eli Goldner, Guergana Savova. 2025. Overview of the 2025 Shared Task on Chemotherapy Treatment Timeline Extraction. Proceedings of the 7th Clinical Natural Language Processing Workshop, 2025.
Please use ACL Pubcheck Tool to ensure that your paper is properly formatted.
Clinical NLP 2025 has no preprint restrictions; you may post to arXiv at any time.
Further instructions:
Each participating team can submit one paper describing their approaches and systems for one or more subtasks. The paper should be titled:
TEAM at Chemotimelines 2025: Sub-Title
TEAM at Chemotimelines 2025: Sub-Title
We recommend SemEval paper requirements for advice on what goes into a task paper. Also, here is the link to the MEDIQA paper submission guidelines if it can help: MEDIQA paper guidelines
Please, do not include any real data from the train/dev sets. For illustration purposes, you can create an example that is close to the real one but different enough.
Please, do not publish the models built off the shared task data. We are working through the legal process for publishing models.
1. Submission is through OpenReview, see OpenReview . Submission are due August 21, 2025. When using OpenReview to submit your papers, select the category: "shared task".
2. Please, do not describe the task, it will be described in the overview paper for the shared task. Please, cite:
*Jiarui Yao, *Harry Hochheiser, WonJin Yoon, Eli Goldner, Guergana Savova. 2025. Overview of the 2025 Shared Task on Chemotherapy Treatment Timeline Extraction. Proceedings of the 7th Clinical Natural Language Processing Workshop, 2025.
3. Please, include your results on the dev set as well as the official results on the test set posted under "Leader Board". Because the test set will not be released (to enable future editions of the task), please provide error analysis on the dev set.
4. Papers will be judged by how replicable the system is based on the description. Use the main points posted under "Submission of Test Output". Papers with code are encouraged (but code is not a requirement).
5. Submissions must include clear scientific writing, a short overview of the related work, a full description of the developed models and their originality/specificity, description of additional data/models that were used, and a discussion of the results. It is important to describe the details well enough that the system could be replicated. You can report additional experiments and results in your papers, but please make it clear that they were obtained before/after the competition.
6. The shared task will follow a double-blind review process, papers must not include authors' names and affiliations. Reporting your team's name, rank, and results is allowed and will not be considered as disclosure of identity.
7. We would expect that most papers will be included in the proceedings.
8. Teams with accepted papers will be invited to present their work either as presentations or posters. Paper selection for oral presentations will be based on the following criteria: approach novelty, research insights, and obtained results.
9. Code: Publishing your code is encouraged but not required for your paper acceptance. If you are planning to make your GitHub repo public before the publication of your paper, you can cite your shared task paper as follows: Title. Authors. Submitted to ClinicalNLP 2025.
Q&A:
Q1: We are in the process of submitting the paper describing our proposed solutions, but only one of us add a pre-existing OpenReview account, while the other ones are waiting for account creation that can take up to two weeks given that our institution is not registered in OpenReviews (and co-authors can not be added if their OpenReviews account does not exist). Would you be able to add co-authors after the submission is made ?
Answer to Q1: Yes, PCs have the power to add additional authors later, so if they can’t get an account by the deadline, they can send us the OpenReview IDs when they have them and we can add them.
Q2: OpenReview says that: "Search author profile by first, middle and last name or email address. All authors must have an OpenReview profile prior to submitting a paper." It is a double blind review so during the submission in OpenReview, we list all the authors? and on the paper something like this: "Anonymous NAACL Submission"
Answer to Q2: Yes, list all authors on OpenReview but anonymize the submission. OpenReview will not display the authors in the metadata to reviewers.
Q3: Does mentioning the team name in the title compromise the integrity of the double-blind review process?
Answer to Q3:
If the team name reveals the authors' identity, we kindly ask that you temporarily replace it with an anonymized name (e.g., Anonymous Team 1).
If the team name does not reveals the authors' identity, the answer is no.
Please note: After acceptance, there will be a final version submission stage. At that stage, you will be welcome to include your team name.
Here are the MEDIQA paper submission guidelines if it can help: MEDIQA paper submission guidelines
Q4: Are shared task participants expected to review other teams' papers? What is the deadline?
Answer to Q4: Yes, shared task participants are expected to review other teams' papers. Reviews are due by Sept 18. Please, check your assignments on OpenReview.