The 3rd Financial Narrative Processing Workshop (FNP 2021)
NEW: The FNP 2021 workshop and shared tasks proceedings are now on ACL Anthology: https://aclanthology.org/2021.fnp-1.0/
NEW: FNP 2021 Recordings of invited Talks, Panel Discussion and Paper presentations are on YouTube video play (the videos are orders according to the FNP 2021 Programme):
FNP 2021 YouTube Playlist can be accessed here as well: https://www.youtube.com/playlist?list=PLO93yuPJT61-YCP5AAtUUr0rMVUSqXvQk
The 3rd Financial Narrative Processing Workshop (FNP 2021) was 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.
Sponsors:
FNP 2021 is sponsored by:
The Data Science Institute and yseop.com
Date and Location:
15 – 16 September 2021
This will be a free-to-all online event. We’ll update you here in case of any change as we are still considering possibilities for a hybrid event.
🔔Free registration now open:
FNP 2021 full preliminary programme, keynote speakers bios, talks and abstracts can be found here: https://bit.ly/3enWEEc
List of invited speakers:
Emmanuel Walckenaer, CEO, Yseop, Paris, France Emmanuel joined Yseop as CEO in 2017, leading the company’s growth and vision to bring the benefits of automation and NLG to enterprise companies globally. He brings over 25 years of international experience in high-tech service and business development. Emmanuel joined Yseop in 2017 from Sierra Wireless, where he was General Manager and Senior Vice President of the Cloud & Connectivity Services business unit. He led the growth of this unit across Europe and North America through strategic acquisitions and the development of a bespoke cloud and connectivity offering for the expanding Internet of Things (IOT) market. |
Prof Jochen L Leidner – Coburg University of Applied Sciences | University of Sheffield Jochen is Professor of Explainable and Responsible Artificial Intelligence in Insurance at Coburg University of Applied Sciences, Germany and a Visiting Professor of Data Analytics, Department of Computer Science, University of Sheffield, UK. He is also founder and Director of Polygon Analytics and KnowledgeSpaces. He has over a decade of scientific and managerial experience in the legal and financial data industry in the US, the UK and Switzerland. He holds a MPhil from the University of Cambridge and a PhD from the University of Edinburgh, and is twice winner of the Thomson Reuters “Inventor of the Year” award. |
Dr Kim Trottier – HEC Montréal. Montréal, Canada Kim is an accounting associate professor at HEC Montréal Business School. With a background in capital markets, firm performance, and advanced analytics, she will provide cross-over expertise on financial reporting and artificial intelligence. |
Dr Claire Hardy – Lancaster University. Lancaster, UK Claire is a Lecturer in Organisational Health and Wellbeing within Lancaster University’s Centre for Organisational Health and Wellbeing. Claire is a charted Occupational Psychologist by background and is an award-winning researcher in her field. |
Prof Antonio Moreno – UAM. Madrid, Spain Antonio is a Professor of Linguistics and Director of the Computational Linguistics Lab at University Autonomous of Madrid (UAM), and Director of the UAM-IIC Chair in Computational Linguistics. He is a former Fulbright postdoc scholar at the Computer Science Dept., New York University and a former DAAD scholar at Augsburg Universität. |
Prof Steven Young – Lancaster University. Lancaster, UK Steve is a Professor in accounting at Lancaster University and has a track record on working with financial narratives, financial reporting quality and has strong links with the UK’s FRC, FCA, PLSA and IRS. |
Dr Raymond Ng– Signal AI, London, UK. Raymond is a Senior Data Scientist at Signal AI in London. His research areas cover speech technology and natural language processing. Before joining Signal, Ray was a postdoc researcher in the University of Sheffield. Ray was the PI/co-PI of six research projects (£380k funding) and he co-supervised various MSc/PhD projects on speech, language technology and machine learning topics. Ray is the recipient of Tech Nation UK “Exceptional Talent for Digital Technology” Tier 1 visa endorsement. He was the guest speaker of the Royal Institute Christmas Lectures 2017, the Intelligent Sensing Summer School QMUL 2019 and the London Text Analytics Meetup 2020. |
Dr Vasiliki Athanasakou, Saint Mary’s University. Halifax, Canada Vasiliki is an associate professor in accounting at Saint Mary’s University and has a track record on working with financial narratives, financial reporting quality and the impact of regulation on capital markets and organisational performance. |
Important Dates:
First call for abstracts 26 April 2021First call for shared task participants 1 May 2021Second call for abstracts 26 May 2021Second call for shared task participants 1 June 2021Abstracts submission deadline 10 August 2021 (extended)Abstracts notification of acceptance: 12 August 2021Shared task results & winning teams: 15 August 2021Workshop and shared task dates: 15 September 2021
Workshop Description:
Following the success of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation (FNP-FNS 2020), the First FNP 2018 at LREC’18 in Japan, the Second FNP 2019 at NoDaLiDa 2019 in Finland and as well as the Multiling 2019 Financial narrative Summarisation task at RANLP in Bulgaria, we have had a great deal of positive feedback and interest in continuing the development of the financial narrative processing field, especially from our shared task participants.
The 1st FNP-FNS workshop at COLING 2020 was a great success. We ran 3 different shared tasks focusing on text summarisation, structure detection and causal sentence detection, namely FNS, FinToc and FinCausal shared tasks respectively. The shared tasks attracted more than 100 teams from different universities and organisations around the globe. The shared tasks resulted in the first large scale experimental results and state of the art methods applied mainly to financial data. This shows the importance and growth of this field.
Shared Tasks Competition:
We introduce 3 shared tasks. The winning team from each shared task will receive an achievement certificate and a money prize worth US$650.
- Financial Narrative Summarisation (FNS 2021)
- Causality Identification in Financial documents (FinCausal 2021).
- Financial Document Structure Extraction (FinTOC 2021)
Awards and Prizes:
The winning team from each shared task will receive an achievement certificate and a money prize worth US$650. Each team will also be given the chance to present their work at the workshop.
Motivation and topics of interest:
There is a growing interest in the application of automatic and computer-aided approaches for extracting, summarising, and analysing both qualitative and quantitative financial data. In recent years, previous manual small-scale research in the Accounting and Finance literature has been scaled up with the aid of NLP and ML methods.
For this year we are introducing a 2 day event where we invite one-page (500 words) abstract submissions on topics that include, Natural Language Processing (NLP), Machine Learning (ML), and Corpus Linguistics (CL) methods related to all aspects of financial text mining and financial narrative processing (FNP) in addition to demonstrating the value and challenges of applying summarisation to multilingual financial text, usually referred to as financial narrative disclosures.
Organising Committee:
- Dr Mahmoud El-Haj, Lancaster University (General Chair)
- Prof Paul Rayson, Lancaster University (FNP Program Chair)
- Nadhem Zmandar, Lancaster University (Publication Chair and FNS Organiser)
- Dr Houda Bouamor, CMU, Qatar (FNP Program Chair)
- Dr Marina Litvak, Shamoon Academic College of Engineering (FNS Organiser)
- Dr George Giannakopoulos, NCSR Demokritos (FNS Organiser)
- Dr Ahmed AbuRaed, Universitat Pompeu Fabra (FNS Organiser)
- Nikiforos Pittaras, NCSR Demokritos (Publicity Chair)
- Dr Ismail El Maarouf, Fortia Financial Solution (FinToc Organiser)
- Abderrahim Aitazzi, Fortia (FinTOC Shared Task Organizer)
- Dr Juyeon Kang, Fortia Financial Solution (FinToc Shared Task Organiser)
- Dominique Mariko, Yseop Lab (FinCausal Shared Task Organizer)
- Hanna Abi-Akl, Yseop Lab (FinCausal Shared Task Organizer)
- Hugues de Mazancourt, Yseop Lab (FinCausal Shared Task Organizer)
- Estelle Labidurie, Yseop Lab (FinCausal Shared Task Organizer)
Call For Abstracts
We invite abstract submissions on topics that include, but are not limited to, the following:
- Applying core technologies on financial narratives: morphological analysis, disambiguation, tokenization, POS tagging, named entity recognition, chunking, parsing, semantic role labelling, sentiment analysis, document quality and advanced readability metrics etc.
- Using NLP to detect misreporting in relation to diversity and wellbeing on issues related to gender, ethnicity, women at work as well as employee mental health and stability.
- Financial narratives resources: dictionaries, annotated data, tools and technologies etc.
- Given the international nature of the conference, we particularly welcome FNP papers reporting non- English and multilingual research, describing the different regulatory regimes within which companies operate internationally.
- Summarisation across domains and sources that are related to finance (e.g. company blogs, product reviews, market briefs, etc.), this includes financial multilingual and cross-lingual summarisation using single-document summarisation, multi-document summarisation, summarisation evaluation, headline generation, cross-domain/cross-topic summarisation.
Abstract Submission Instructions:
We invite abstracts describing original, completed or ongoing, unpublished research. We welcome abstract submissions, in theory, methodology, as well as resources and applications in all areas related to Financial Natural Language Processing and Financial Text Analysis. We also welcome abstract submissions on negative results as well as submissions highlighting challenges faced in industrial or academic settings. Abstract should be 1 page long and a maximum of 500 words. In your abstract please explain the topic you are looking forward to present, is it a complete, ongoing or future work, what audience are you targeting (e.g. NLP, Summarisation, Accounting and Finance …etc) and findings and conclusions that emerged from your work. Abstracts must be submitted through the EasyChair submission system and will be reviewed by the Programme Committee. All submissions will be reviewed on the basis of both individual criteria and global criteria https://easychair.org/conferences/?conf=fnp2021.
Authors of accepted abstracts will be asked to submit a 4-8 paper describing their work in details including methodologies, results and findings. All accepted papers will be published in an open access and indexed proceedings. The workshop is free to attend and no registration fees are required.
To submit an abstract please click on the submit button or use the EasyChair submission URL below:
Submission URL: https://easychair.org/conferences/?conf=fnp2021
We will go through the abstracts and notify participants by 15 July 2021. Accepted abstract will be presented during the workshop event.
List of accepted abstracts:
| Jiahui Hu, Patrick Paroubek and Dirk Schumacher | Annotation model and corpus for opinionated economy and finance narrative detection |
| Ankush Chopra, Sohom Ghosh and Prateek Nagwanshi | Data Driven Content Creation using Statistical and Natural Language Processing Techniques for Financial Domain |
| Danxin Cui, Dominique Mariko, Estelle Labidurie, Hugues de Mazancourt and Patrick Paroubek | A sequence to sequence transformer data logic experiment |
| Kiyoshi Izumi, Hitomi Sano and Hiroki Sakaji | Economic Causal-Chain Search and Economic Indicator Prediction using Textual Data |
| Jan Štihec, Senja Pollak and Martin Žnidaršič | Preliminary experimentation with combinations and extensions of forward-looking sentence detection wordlists |
| Esme Manandise | On Estimating Sentence Complexity of Domain-Specific Single Sentences: Are Complexity Factors Relevant to Automated Agents Relevant to Human Agents? |
Programme Committee:
- Andrew Moore (Lancaster University, UK)
- Vasiliki Athanasakou (SMU, Canada)
- Catherine Salzedo (LUMS, Lancaster University, UK)
- Haithem Afli (Cork Institute of Technology, Ireland)
- Steven Young (LUMS, Lancaster University, UK)
- Mohan Subbiah (LUMS, Lancaster University, UK)
- Paulo Alves (Universidade Católica Portuguesa, Portugal)
- Thomas Schleicher (MBA, Manchester University)
- Natalia Vanetik (Sami Shamoon College of Engineering, Israel)
- George Petasis (NCSR Demokritos, Greece)
- Peter Rankel (Elder Research Inc., USA)
- Mahmoud El-Haj (Lancaster University, UK)
- Paul Rayson (Lancaster University, UK)
- Nadhem Zmandar (Lancaster University, UK)
- Houda Bouamor (CMU, Qatar)
- Marina Litvak (Shamoon Academic College of Engineering, Israel)
- George Giannakopoulos (NCSR Demokritos, Greece)
- Ahmed AbuRaed (Universitat Pompeu Fabra, Spain)
- Nikiforos Pittaras(NCSR Demokritos, Greece)
- Ismail El Maarouf (Fortia Financial Solution, France)
- Abderrahim Aitazzi (Fortia Financial Solution, France)
- Juyeon Kang (Fortia Financial Solution, France)
- Dominique Mariko (Yseop Lab, France)
- Hanna Abi-Akl (Yseop Lab, France)
- Hugues de Mazancourt (Yseop Lab, France)
- Estelle Labidurie (Yseop Lab, France)
Anti-Harassment Policy:
The workshop supports the ACL anti-harassment policy.