Financial concepts extraction and lexical simplification in Spanish
Abstrak
This paper delves into concept extraction and lexical simplification in the financial domain in Spanish. In our approach, concept extraction involves identifying relevant terms and phrases using AI language models, while lexical simplification aims to make complex financial concepts more accessible. For this study, terms were annotated in the FinT-esp financial corpus and the mT5 neural model was used for accurate term extraction. The model yielded remarkable results: 96% of the detected terms had not been manually annotated before, showcasing its noteworthy generative capability. For lexical simplification, the paper proposes three main strategies: paraphrasing, synonym substitution, and translation, all integrated into an interactive interface that addresses the issue of sentence length. This research significantly contributes to financial concept detection and offers an effective method for simplifying financial language in Spanish.
Penulis (2)
Blanca Carbajo Coronado
Antonio Moreno Sandoval
Akses Cepat
- Tahun Terbit
- 2024
- Bahasa
- en
- Sumber Database
- CrossRef
- DOI
- 10.58859/rael.v23i1.590
- Akses
- Open Access ✓