--------Apologies for cross posting-----
Dear Colleagues,
We are excited to announce *Financial Causality Detection (FinCausal 2025) shared task* to be organized in the upcoming the *6th Financial Narrative Processing (FNP)* https://www.lllf.uam.es/wordpress/fincausal-25/held in conjunction with COLING-2025 in Abu Dhabi, UAE, on January 19-20, 2025.
For the 6th FNP shared task, we will continue working in two languages ( *English*, *Spanish*) and we will introduce a new FinCausal Shared Task: Financial Causality Detection (FinCausal 2025) on hybrid question answering.
The objective is to detect causal effects in financial disclosures in English and Spanish. The dataset is a combination of extractive and generative QA. Questions will be formulated abstractedly, while answers will be extractive. In certain segments, questions will either focus on causes or effects, and the answers will be directly extracted from the text. The evaluation metric for responses will encompass both exact matching and semantic similarity.
The shared tasks attracted more than 150 participants within the last 3 FNP editions, for this year we are expanding the dataset by making the tasks more challenging.
→ *2 new datasets* will be developed, one in English and one in Spanish
Access the CodaLab by clicking here https://codalab.lisn.upsaclay.fr/competitions/19936
*Key Dates*
First CFP: 15 July 2024 Second CFP: 15 August 2024 (FinCausal) Practice set release: *2 September 2024* (FinCausal) Training set release: *15 September 2024* (FinCausal) Blind test set release: *30 October 2024* (FinCausal) Systems submission: *7 November 2024* (FinCausal) Release of results: *12 November 2024* (FinCausal and general) Paper Submission Deadline: *25 November 2024* Notifications of Acceptance: *5 December 2024* Camera-ready Paper Deadline: *13 December 2024*
As in previous editions, FNP 2025 will be on-site and in-person (there will be NO option for it to be virtual or hybrid).
More info: https://www.lllf.uam.es/wordpress/fincausal-25/fnp-2025/
Best Regards,
Paloma Martínez
Full professor Human Language and Accessibility Technologies Group (hulat.inf.uc3m.es http://labda.inf.uc3m.es) Computer Science Department Universidad Carlos III de Madrid @Grupo_HULAT