Conference paper Open Access
L3i_LBPAM at the FinSim-2 task: Learning Financial Semantic Similarities with Siamese Transformers
Nhu Khoa Nguyen; Emanuela Boros; Gaël Lejeune; Antoine Doucet; Thierry Delahaut
In this paper, we present the different methods proposed for the FinSIM-2 Shared Task 2021 on Learning Semantic Similarities for the Financial domain. The main focus of this task is to evaluate the classification of financial terms into corresponding top-level concepts (also known as hypernyms) that were extracted from an external ontology. We approached the task as a semantic textual similarity problem. By relying on a siamese network with pre-trained language model encoders, we derived semantically meaningful term embeddings and computed similarity scores between them in a ranked manner. Additionally, we exhibit the results of different baselines in which the task is tackled as a multi-class classification problem. The proposed methods outperformed our baselines and proved the robustness of the models based on textual similarity siamese network.
| Name | Size | |
|---|---|---|
|
LearningFinancialSemanticSimilaritieswithSiameseTransformers.pdf
md5:ead3358139d7332a5f0becfb8c769d61 |
558.5 kB | Download |
| All versions | This version | |
|---|---|---|
| Views | 12 | 12 |
| Downloads | 9 | 9 |
| Data volume | 5.0 MB | 5.0 MB |
| Unique views | 11 | 11 |
| Unique downloads | 8 | 8 |
- Publication date:
- April 16, 2021
- DOI:
-
- Grants:
-
European Commission:
-
NewsEye - NewsEye: A Digital Investigator for Historical Newspapers (770299)
- EMBEDDIA - Cross-Lingual Embeddings for Less-Represented Languages in European News Media (825153)
-
NewsEye - NewsEye: A Digital Investigator for Historical Newspapers (770299)
- Meeting:
- The 1st Workshop on Financial Technology on the Web (FinWeb) with FinSim-2 and FinSBD-3 Shared Task, in conjunction with WWW '21: The Web Conference 2021, Ljubljana, Slovenia (online), 12-16 April 2020
- Communities:
- License (for files):
- Creative Commons Attribution 4.0 International