The 3rd Financial Narrative Processing Workshop (FNP-2021)

Welcome to the 3rd Financial Narrative Processing Workshop (FNP 2021). This year we are running a 2 day event sponsored and funded by the Data Science Institute (DSI) at Lancaster University and Yseop. This is an international gathering of researchers and keynote speakers working on Financial Narratives from computing, accounting & finance.

Shared Task paper submission now open.

Why Submit  a shared task paper:

Each team participating in any of the 3 Shared Tasks for FNP 2021 is encouraged to submit a short paper:

  • The paper helps readers understand your methodology and verify your system.
  • Readers and other researchers will use your paper and system description to try and replicate your work.
  • All submitted papers will appear in an archived proceedings on ACL Anthology.

Submission Format:

Authors should follow EMNLP 2021 format. Author kit can be found on: https://2021.emnlp.org/call-for-papers/style-and-formatting

Paper Length:

As this is a system description paper we require that your paper is up to 4 pages long plus any number of pages for references.

Appendix is allowed but only one appendix of a maximum of 1 page on top of the 4.

How to submit a Shared task paper:

To submit a paper click on Submission URL: https://easychair.org/conferences/?conf=fnp2021

Please check the shared task page for submission deadline. http://wp.lancs.ac.uk/cfie/shared-tasks/

In order to make sure your paper goes into the correct shared task track please add the shared task name in the keyword section of the submission form.

For example if you are submitting a paper to the FinCausal shared task please make sure the keyword ‘FinCausal’ is added as the last keyword. For the other shared tasks use FNS or FinToc. Example below:

Provisional Structure:

The following structure is just to help you organise your paper but you are free to choose a different one:

  • Abstract: up to 300 words highlighting your approach and key results.
  • Introduction: less than a page expanding on the abstract mentioning key background such as why the task is challenging for current modelling techniques and why your approach is interesting/novel.
  • Data: review of the data you used to train your system. Be sure to mention the size of the training, validation and test sets that you’ve used, and the label distributions, as well as any tools you used to pre-process the data.
  • System: a detailed description of how your system was built and trained. If you’re using a neural network, were there pre-trained embeddings, how was the model trained, what hyperparameters were chosen and experimented with? How long did the model take to train, and on what infrastructure? Linking to source code is valuable here as well, but the description should be able to stand alone as a full description of how to replicate the system.
  • Results: a description of the key results of the paper. If you have done extra error analysis into what types of errors the system makes, this is extremely valuable for the reader. Unofficial results from after the submission deadline can be very useful as well.
  • Discussion: general discussion of the task and your system. Description of characteristic errors and their frequency over a sample of development data. What would you do if you had another 3 months to work on it?
  • Conclusion: a restatement of the introduction, highlighting what was learned about the task and how to model it.

Citation and References to include in your paper:

Please cite the shared task papers in your system description (make sure you cite the relevant ones only):

FNS-Summarisation 2021 shared task:

@inproceedings{elhaj-fns-2021, title ={{The Financial Narrative Summarisation Shared Task (FNS 2021)}}, author = {El-Haj, Mahmoud and Zmandar, Nadhem and Rayson, Paul and AbuRa'ed, Ahmed and Litvak, Marina and Pittaras, Nikiforos and Giannakopoulos, George}, booktitle ={{The Third Financial Narrative Processing Workshop (FNP 2021)}}, year = {2021}, address = {Lancaster, UK} }

@inproceedings{elhaj-fns-2020, title ={{The Financial Narrative Summarisation Shared Task (FNS 2020)}}, author = {El-Haj, Mahmoud and AbuRa'ed, Ahmed and Litvak, Marina and Pittaras, Nikiforos and Giannakopoulos, George}, booktitle ={{The 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation (FNP-FNS 2020)}}, year = {2020}, address = {Barcelona, Spain} }

Fin-Causal 2021 Shared Task:

@inproceedings{Mariko-fincausal-2021, title ={{The Financial Document Causality Detection Shared Task (FinCausal 2021)}}, author = {Mariko, Dominique and Abi Akl, Hanna and Labidurie, Estelle and de Mazancourt, Hugues and El-Haj, Mahmoud}, booktitle ={{The Third Financial Narrative Processing Workshop (FNP 2021)}}, year = {2021}, address = {Lancaster, UK} }

@inproceedings{Mariko-fincausal-2020, title ={{The Financial Document Causality Detection Shared Task (FinCausal 2020)}}, author = author = {Mariko, Dominique and Abi Akl, Hanna and Labidurie, Estelle and Durfort, Stephane and de Mazancourt, Hugues and El-Haj, Mahmoud}, booktitle ={{The 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation (FNP-FNS 2020)}}, year = {2020}, address = {Barcelona, Spain} }

 

Fin-Toc 2021 Shared Task:

@inproceedings{fintoc-2021, title ={{The Financial Document Structure Extraction Shared Task (FinToc 2021)}}, author = {El Maarouf, Ismail and Kang, Juyeon and Aitazzi, Abderrahim and Bellato, Sandra and Gan, Mei and El-Haj, Mahmoud}, booktitle ={{The Third Financial Narrative Processing Workshop (FNP 2021)}}, year = {2021}, address = {Lancaster, UK} }

@inproceedings{fintoc-2020, title ={{The Financial Document Structure Extraction Shared Task (FinToc 2020)}}, author = {Bentabet, Najah-Imane and Juge, Remi and El Maarouf, Ismail and Mouilleron, Virginie and Valsamou-Stanislawski, Dialekti and El-Haj, Mahmoud}, booktitle ={{The 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation (FNP-FNS 2020)}}, year = {2020}, address = {Barcelona, Spain} }

Attending workshop and presenting your work:

At least one author for each paper is required to register (for free) at https://www.eventbrite.co.uk/e/163066884441.

The winners of each shared task will present their work by giving a live oral presentation.

Each of the shared task participants who submits a short paper describing their work will be given access to Gather Town where they’ll have a booth to present their poster.

Participants should prepare an A0 or A1 poster in a PDF file format.

**More details soon on how to access Gather Town soon**