L3i_LBPAM at the FinSim-2 task: Learning Financial Semantic Similarities with Siamese Transformers - Sorbonne Université
Conference Papers Year : 2021

L3i_LBPAM at the FinSim-2 task: Learning Financial Semantic Similarities with Siamese Transformers

Abstract

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. CCS CONCEPTS • Computing methodologies → Lexical semantics; Neural networks.
Fichier principal
Vignette du fichier
Nguyen et al. - 2021 - L3i_LBPAM at the FinSim-2 task Learning Financial.pdf (545.44 Ko) Télécharger le fichier
Origin Publisher files allowed on an open archive

Dates and versions

hal-03256324 , version 1 (10-06-2021)

Identifiers

Cite

Nhu Khoa Nguyen, Emanuela Boros, Gaël Lejeune, Antoine Doucet, Thierry Delahaut. L3i_LBPAM at the FinSim-2 task: Learning Financial Semantic Similarities with Siamese Transformers. WWW '21: The Web Conference 2021, Apr 2021, Ljubljana (virtual), Slovenia. pp.302-306, ⟨10.1145/3442442.3451384⟩. ⟨hal-03256324⟩
26 View
165 Download

Altmetric

Share

More