Introduction

The FinSim 2020 shared task is colocated with the FinNLP workshop and offers the challenge to automatically learn effective and precise semantic models to process documents from the financial domain. This task hopes to spark interest from communities in NLP, ML/AI, Knowledge Representation and Financial document processing.

Going beyond the mere representation of words is a key step to industrial applications that make use of Natural Language Processing (NLP). This is typically addressed using either

• Unsupervised corpus-derived representations like word embeddings, which are typically opaque to human understanding but very useful in NLP applications;

• Manually tagged resources such as corpora, lexica, taxonomies and ontologies, which typically have low coverage and contain inconsistencies, but provide a deeper understanding of the target domain.

These two methods form the two ends of a spectrum which a number of approaches have attempted to combine, particularly in tasks aiming at expanding the coverage of manual resources using automatic methods.

• The Semeval community has organized several evaluation campaigns to stimulate the development of methods which extract semantic/lexical relations between between concepts/words (Bordea et al. 2015, Bordea et al. 2016, Jurgens et al. 2016, Camacho-Collados et al. 2018).

• There are also a large number of datasets and challenges that specifically look at how to automatically populate knowledge bases such as DBpedia or Wikidata (e.g. KBP challenges).

• To the best of our knowledge, FINSIM 2020 is the first time such a task is proposed for the Financial domain.

Description

Participants will be given a list of carefully selected terms from the Financial domain such as “European depositary receipt”, “Interest rate swaps” and will be asked to design a system which can automatically classify them into the most relevant hypernym (or top-level) concept in an external ontology. For example, given the set of concepts “Bonds”, “Unclassified”, “Share”, “Loan”, the most relevant hypernym of “European depositary receipt” is “Share”.

Participants will be given a large corpus of in-domain data to facilitate learning semantic representations as well as a set of concepts extracted from an ontology (The Financial Industry Business Ontology (FIBO)).

Systems will be evaluated according to the accuracy with which financial terms are classified, and according to recall (based on the total number of predictions). We are interested in systems which make creative use of relevant resources such as ontologies and lexica, as well as systems which make use of large existing word embeddings such as BERT (Devlin et al. 2018).

Registration

To register your interest in participating in FinSim shared task please use the following google form: https://forms.gle/sBC459xK8YuVw3Zz8

References

Georgeta Bordea, Paul Buitelaar, Stefano Faralli and Roberto Navigli (2015). “SemEval-2015 Task 17: Taxonomy Extraction Evaluation (TExEval)”. In Proceedings of SemEval 2015, co-located with NAACL HLT 2015, Denver, Col, USA.

Georgeta Bordea, Els Lefever, and Paul Buitelaar (2016). “Semeval-2016 task 13: Taxonomy extraction evaluation (TExEval-2)”. In Proceedings of the 10th International Workshop on Semantic Evaluation, San Diego, CA, USA.

Jose Camacho-Collados, Claudio Delli Bovi, Luis Espinosa-Anke, Sergio Oramas, Tommaso Pasini, Enrico Santus, Vered Shwartz, Roberto Navigli, and Horacio Saggion (2018). “SemEval-2018 Task 9: Hypernym Discovery”. In Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), New Orleans, LA, United States. Association for Computational Linguistics.

Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova (2018). “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding”. https://arxiv.org/abs/1810.04805v2.

David Jurgens and Mohammad Taher Pilehvar (2016). “SemEval-2016 Task 14: Semantic Taxonomy Enrichment”. In Proceedings of SemEval-2016, NAACL-HLT.

The Financial Industry Business Ontology (FIBO)

Prize

A USD$1000 prize will be rewarded to the best-performing teams.

Important Dates

• March 13th, 2020: Registration opens.

• April 16th, 2020: Release of training set & scoring scripts.

• May 18th, 2020: Release of test set.

• May 22th, 2020: Registration deadline.

• May 22th, 2020: System Submission deadline.

• May 27th, 2020: Release of results.

• 31 May 2020 - Shared task title and abstract due

• 8 June 2020 - Shared task paper submissions due

• 15 June 2020 - Camera-ready version of shared task paper due

• 5-10 January 2021 - FinNLP 2020 Workshop (Kyoto, Japan or virtual)

Shared Task Co-organizers - Fortia Financial Solutions

• Ismail EL MAAROUF

• Youness MANSAR

• Virginie MOUILLERON

• Dialekti VALSAMOU-STANISLAWSKI

Leaderboard