ConvFinQA shared task is closed.
Congratulations to the winning team:
HIT-SCIR, Dingzirui Wang, Longxu Dou, and Wanxiang Che from Harbin Institue of Technology
Guidelines
ConvFinQA is a large-scale dataset on conversational QA over financial data, aiming to automate the analysis of a large corpus of financial documents. Please check our ConvFinQA paper for more details. The dataset, code, and instructions can be found on Github.
Submission
The leaderboard for the test set is hosted on Codalab. A submission needs to consist of results on the entire test set to be considered as a valid submission. This phase is aimed at the final evaluation of the model and one is not allowed to create multiple submissions using multiple teams.
Please submit your results to the leaderboard. Then please use the ACM Conference Proceeding templates (two column format) to format your papers. Submissions should have no more than 6 pages including references. Please submit through this link, and also upload to arxiv. To be eligible for result archives and consideration for awards, we kindly request you to send the following information to czyssrs07@gmail.com using your main contact email:
- Team name.
- Team members.
- The username used in CodaLab submissions.
- The forum link to your paper submission on this link and the link to your arxiv submission.
Dual Submission: We also allow submissions that are under review in other venues or have preprint versions. But please make sure to follow dual submission policies from other venues. Non-Archival: The paper submission will be non-archival. The winners can present their work at the workshop. Anonymity Period: We do not enforce an anonymity period. We allow preprint servers such as arXiv at any point of time.
Prize
There will be one champion, one runner-up, and one honorable mention for this challenge. We will have awards for these winners.
Sponsors
