Call For Participation FinCausal 2020 Shared Task at FNP-FNS COLING 2020

FinCausal 2020


Artificial Intelligence



Call For Participation: FinCausal 2020 Shared Task at FNP-FNS COLING 2020
Please consider participating in FinCausal 2020 shared task.
The task focuses on Causality Identification in Financial documents as part of The 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation (FNP-FNS 2020), to be held at COLING'2020, Barcelona, Spain on 13 September 2020.
- Workshop URL: http://wp.lancs.ac.uk/cfie/fnp2020/
- Shared Task URL: http://wp.lancs.ac.uk/cfie/fincausal2020/
- Participation form: http://bit.ly/2qX9O5s
IMPORTANT DATES:
• First call for shared task participants Dec 1, 2019
• Release of Trial Data Feb 1, 2020
• Release of Training Data March 1, 2020
• Second call for shared task participants Mar 18, 2020
• Release of Test Data April 1, 2020
• Contributions from participants are expected April 20, 2020
• Shared task results due May 1, 2020
• Shared task papers due May 15, 2020
• Notification of acceptance Jun 24, 2020
• Camera-ready papers due Jul 11, 2020
• Workshop and shared task dates Sep 13, 2020
______________________________________________________________________
SHARED TASK DESCRIPTION
This shared task proposes data to experiment on causality detection, and focuses on determining causality associated to an event or to transformations of financial objects.
The data are extracted from a corpus of 2019 financial news provided by QWAM http://www.qwamci.com/.
______________________________________________________________________
SUBTASKS
The task contains two subtasks:
a) Sentence classification
This task is a binary classification task. The goal of this subtask is to filter sentences which display causal meanings (1) from the sentences that are noise in regard of causality (0)
b) Cause – effect detection
This task is a relation extraction task. The aim is to identify, in a text block defined as causal (causal sentence or paragraph), the substring displaying the cause and the substring describing the effect.
______________________________________________________________________
DATASET
Two datasets, one for each sub-task, will be released as csv files in three parts each: trial set, training set and test set.
______________________________________________________________________
ORGANISING TEAM:
- Dominique Mariko, Yseop
- Anubhav Gupta, Yseop
- Hanna Abi-Akl, Yseop
- Hugues de Mazancourt, Yseop
______________________________________________________________________
CONTACT and REGISTRATION:
Participant can register to this shared task by filling the participation form, and get access to the datasets
For any questions please contact Organisers: fin.causal.task@gmail.com
______________________________________________________________________
MORE DETAILS ON THE SUB-TASKS ON:
http://wp.lancs.ac.uk/cfie/fincausal2020/
and
https://drive.google.com/file/d/1LUTJVj9ItJMZzKvy1LrCTuBK2SITzr1z/view