The Second Financial Narrative Processing Workshop (FNP 2019)
To be held at the The 22nd Nordic Conference on Computational Linguistics (NoDaLiDa’19) Conference, Turku University, Turku, Finland, on 30 September 2019.
NEW: Workshop final program is now out: FNP2019_program
March 25, 2019: First Call for Workshop Papers June 5, 2019: Second Call for Workshop Papers August 16, 2019 (aoe): Workshop Paper Submissions Deadline [Extended] August 26, 2019: Notification of Acceptance September 6, 2019 (aoe): Camera Ready Papers
September 18, 2019 Workshop Schedule
Monday September 30, 2019: Workshop Date (Full-day).
Following the success of the First FNP 2018 at LREC’18, Japan, we have had a great deal of positive feedback and interest in continuing the development of the financial narrative processing field. This prompted us to hold a training workshop in textual analysis methods for financial narratives that was oversubscribed showing that there is an increasing interest in the subject. As a result, we are now motivated to organise the Second Financial Narrative Processing Workshop, FNP 2019.
The workshop will continue focusing on the use of 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). 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 example to examine approaches to retrieving structured content from financial reports, and to study the causes and consequences of corporate disclosure and financial reporting outcomes. One focal point of the workshop is to develop a better understanding of the determinants of financial disclosure quality and the factors that influence the quality of information disclosed to investors beyond the quantitative data reported in the financial statements. The workshop will also encourage efforts to build resources and tools to help advance the work on financial narrative processing (including content retrieval and classification) due to the dearth of publicly available datasets and the high cost and limited access of content providers. The workshop aims to advance research on the lexical properties and narrative aspects of corporate disclosures, including glossy (PDF) annual reports, US 10-K and 10-Q financial documents, corporate press releases (including earning announcements), conference calls, media articles, social media, etc.
For FNP 2019 we will collaborate with Fortia Financial Solutions, a French based company specialised in Financial Investment and Risk management who will work with us on organising a shared task on automatic detection of financial documents structure as part of FNP 2019. http://fortia.fr/
Financial narrative disclosures represent a large part of firms overall financial communications with investors. Textual commentaries help to clarify issues obscured by complex accounting methods and footnote disclosures. In addition, narratives summarise corporate strategy, contextualise results, explain governance arrangements, describe corporate social responsibility policy, and provide forward-looking information for investors. They also provide management with an opportunity to obfuscate accounting results and manipulate readers’ perceptions of underlying economic performance.
General Chair: Dr Mahmoud El-Haj
Publication Chair: Dr Houda Bouamor (Fortia Financial Solution, France)
We invite 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.
- 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.
Submissions may include work in progress as well as finished work. Submissions must have a clear focus on specific issues pertaining to the financial narrative processing whether it is English or multilingual. Descriptions of commercial systems are welcome but authors should be willing to discuss the details of their work. Dual submissions should be disclosed at time of submission.
Submissions must describe substantial, original, completed and unpublished work. Wherever appropriate, concrete evaluation and analysis should be included.
Submissions may consist of no less than four (4) and up to eight (8) pages of content, plus unlimited references.
We follow ACL 2019 submission template as below:
Accepted papers authors are required to submit a camera ready to be included in the final proceedings. Authors of accepted papers will be notified after the notification of acceptance with further details.
Accepted papers will be published on ACL Anthology https://aclanthology.info.
Authors of papers accepted for presentation at FNP 2019 must notify the program chairs by the camera-ready deadline as to whether the paper will be presented. We will not accept for publication or presentation the papers that overlap significantly in content or results with papers that will be (or have been) published elsewhere.
|09:00||09:15||Opening Remarks and Introduction to FNP|
|Session 1 Financial Narrative Processing Papers|
|09:15||09:40||Introduction to Financial Narrative Processing Tools and Resources|
|09:40||10:05||Tone Analysis in Spanish Financial Reporting Narratives|
|Antonio Moreno-Sandoval, Ana Gisbert, Pablo Alfonso Haya, Marta Guerrero and Helena Montoro|
|10:30||10:55||Automated Stock Price Prediction Using Machine Learning|
|Mariam Mokalled, Wassim El-Hajj and Mohamad Jaber|
|10:55||11:20||Utilizing Pre-Trained Word Embeddings to Learn Classification Lexicons with Little Supervision|
|Frederick Blumenthal and Ferdinand Graf|
|11:20||11:45||Towards Unlocking the Narrative of the United States Income Tax Forms with Natural Language Processing|
|11:45||12:10||Active learning for financial investment reports|
|Sian Gooding and Ted Briscoe|
|Session 2 FinTOC Shared Task|
|13:30||13:45||The FinTOC-2019 Shared Task: Financial Document Structure Extraction|
|Remi Juge, Imane Bentabet and Sira Ferradans|
|13:45||14:00||UWB@FinTOC-2019 Shared Task: Financial Document Title Detection|
|Tomas Hercig and Pavel Král|
|14:00||14:15||FinTOC-2019 Shared Task: Finding Title in Text Blocks|
|Hanna Abi Akl, Anubhav Gupta and Dominique Mariko|
|14:15||14:30||FinDSE@FinTOC-2019 Shared Task|
|Carla Abreu, Henrique Cardoso and Eugénio Oliveira|
|14:30||14:45||Daniel@FinTOC-2019 Shared Task : TOC Extraction and Title Detection|
|Emmanuel Giguet and Gaël Lejeune|
|14:45||15:00||Finance document Extraction Using Data Augmented and Attention|
|Ke Tian and Zi Jun Peng|
List of Accepted Papers:
|1||Tomas Hercig and Pavel Král||UWB@FinTOC-2019 Shared Task: Financial Document Title Detection|
|2||Antonio Moreno-Sandoval, Ana Gisbert, Pablo Alfonso Haya, Marta Guerrero and Helena Montoro||Tone Analysis in Spanish Financial Reporting Narratives|
|3||Hanna Abi Akl, Anubhav Gupta and Dominique Mariko||FinTOC-2019 Shared Task: Finding Title in Text Blocks|
|4||Carla Abreu, Henrique Cardoso and Eugénio Oliveira||FinDSE@FinTOC-2019 Shared Task|
|5||Emmanuel Giguet and Gaël Lejeune||Daniel@FinTOC-2019 Shared Task : TOC Extraction and Title Detection|
|6||Esme Manandise||Towards Unlocking the Narrative of the United States Income Tax Forms with Natural Language Processing|
|7||Frederick Blumenthal and Ferdinand Graf||Utilizing Pre-Trained Word Embeddings to Learn Classification Lexicons with Little Supervision|
|8||Sian Gooding and Ted Briscoe||Active learning for financial investment reports|
|9||Rifath Rashid||Company2Vec: Comparable Company Analysis and the Search for Peer Groups|
|10||Mariam Mokalled, Wassim El-Hajj and Mohamad Jaber||Automated Stock Price Prediction Using Machine Learning|
|11||Ke Tian and Zi Jun Peng||Finance document Extraction Using Data Augmented and Attention|
|12||Remi Juge, Imane Bentabet and Sira Ferradans||The FinTOC-2019 Shared Task: Financial Document Structure Extraction|
- Antonio Moreno Sandoval (UAM, Spain)
- Catherine Salzedo (LUMS, Lancaster University, UK)
- Denys Proux (Naver Labs, Switzerland)
- Djamé Seddah (INRIA-Paris, France)
- Eshrag Refaee (Jazan University, Saudi Arabia)
- George Giannakopoulos (SKEL Lab – NCSR Demokritos, Greece)
- Haithem Afli (Cork Institute of Technology, Ireland)
- Houda Bouamor (Fortia Financial Solutions, France)
- Mahmoud El-Haj (SCC, Lancaster University, UK)
- Marina Litvak (Sami Shamoon College of Engineering, Israel)
- Martin Walker (University of Manchester, UK)
- Paul Rayson (SCC, Lancaster University, UK)
- Simonetta Montemagni (Istituto di Linguistica Computazionale – ILC, Italy)
- Sira Ferradans (Fortia Financial Solutions, France)
- Steven Young (LUMS, Lancaster University, UK)