@inproceedings{fdi:010091411,
  title = {{L}everaging multimodality for biodiversity data : exploring joint representations of species descriptions and specimen images using {CLIP}},
  author = {{S}ahraoui, {M}. and {S}klab, {Y}oucef and {P}ignal, {M}. and {V}ignes {L}ebbe, {R}. and {G}uigue, {V}.},
  editor = {},
  language = {{ENG}},
  abstract = {{I}n recent years, the field of biodiversity data analysis has witnessed significant advancements, with a number of models emerging to process and extract valuable insights from various data sources. {O}ne notable area of progress lies in the analysis of species descriptions, where structured knowledge extraction techniques have gained prominence. {T}hese techniques aim to automatically extract relevant information from unstructured text, such as taxonomic classifications and morphological traits. ({S}ahraoui et al. 2022, {S}ahraoui et al. 2023) {B}y applying natural language processing ({NLP}) and machine learning methods, structured knowledge extraction enables the conversion of textual species descriptions into a structured format, facilitating easier integration, searchability, and analysis of biodiversity data.},
  keywords = {},
  volume = {7},
  numero = {},
  pages = {e112666 [4 ]},
  booktitle = {},
  year = {2023},
  DOI = {10.3897/biss.7.112666},
  ISSN = {2535-0897},
  URL = {https://www.documentation.ird.fr/hor/fdi:010091411},
}