# Yseop at FinSim-3 Shared Task 2021: Specializing Financial Domain Learning with Phrase Representations

arXiv: https://arxiv.org/abs/2108.09485 · HTML: https://mlsanity.com/paper/2108.09485/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 11 references that are in the map.
- First posted on arXiv 21 Aug 2021.

## Builds on (most cited first, 4 of 4)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Hierarchical Embeddings for Hypernymy Detection and Directionality](https://mlsanity.com/paper/1707.07273/) (2017)
- [Learning Word Embeddings for Hyponymy with Entailment-Based Distributional Semantics](https://mlsanity.com/paper/1710.02437/) (2017)

## Built on by (most cited first, 2 of 2)

- [Augmenting Interpretable Models with LLMs during Training](https://mlsanity.com/paper/2209.11799/) (2022)
- [Learning Semantic Text Similarity to rank Hypernyms of Financial Terms](https://mlsanity.com/paper/2303.13475/) (2023)

## Abstract (arXiv)

In this paper, we present our approaches for the FinSim-3 Shared Task 2021: Learning Semantic Similarities for the Financial Domain. The aim of this shared task is to correctly classify a list of given terms from the financial domain into the most relevant hypernym (or top-level) concept in an external ontology. For our system submission, we evaluate two methods: a Sentence-RoBERTa (SRoBERTa) embeddings model pre-trained on a custom corpus, and a dual word-sentence embeddings model that builds on the first method by improving the proposed baseline word embeddings construction using the FastText model to boost the classification performance. Our system ranks 2nd overall on both metrics, scoring 0.917 on Average Accuracy and 1.141 on Mean Rank.