Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking

no code implementations • 10 Nov 2023 • Lefteris Loukas, Ilias Stogiannidis, Odysseas Diamantopoulos, Prodromos Malakasiotis, Stavros Vassos

Standard Full-Data classifiers in NLP demand thousands of labeled examples, which is impractical in data-limited domains.

Contrastive Learning Data Augmentation +4

Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance

no code implementations • 28 Aug 2023 • Lefteris Loukas, Ilias Stogiannidis, Prodromos Malakasiotis, Stavros Vassos

We propose the use of conversational GPT models for easy and quick few-shot text classification in the financial domain using the Banking77 dataset.

Contrastive Learning Few-Shot Text Classification +2

Financial misstatement detection: a realistic evaluation

no code implementations • 27 May 2023 • Elias Zavitsanos, Dimitris Mavroeidis, Konstantinos Bougiatiotis, Eirini Spyropoulou, Lefteris Loukas, Georgios Paliouras

In this work, we examine the evaluation process for the task of detecting financial reports with a high risk of containing a misstatement.

FiNER: Financial Numeric Entity Recognition for XBRL Tagging

1 code implementation • ACL 2022 • Lefteris Loukas, Manos Fergadiotis, Ilias Chalkidis, Eirini Spyropoulou, Prodromos Malakasiotis, Ion Androutsopoulos, Georgios Paliouras

We, therefore, introduce XBRL tagging as a new entity extraction task for the financial domain and release FiNER-139, a dataset of 1. 1M sentences with gold XBRL tags.

TAG

DICoE@FinSim-3: Financial Hypernym Detection using Augmented Terms and Distance-based Features

no code implementations • FinNLP 2021 • Lefteris Loukas, Konstantinos Bougiatiotis, Manos Fergadiotis, Dimitris Mavroeidis, Elias Zavitsanos

We present the submission of team DICoE for FinSim-3, the 3rd Shared Task on Learning Semantic Similarities for the Financial Domain.

Word Embeddings

EDGAR-CORPUS: Billions of Tokens Make The World Go Round

1 code implementation • EMNLP (ECONLP) 2021 • Lefteris Loukas, Manos Fergadiotis, Ion Androutsopoulos, Prodromos Malakasiotis

We use EDGAR-CORPUS to train and release EDGAR-W2V, which are WORD2VEC embeddings for the financial domain.

Word Embeddings