Query selection methods for automated corpora construction with a use case in food-drug interactions

Georgeta Bordea (1) , Tsanta Randriatsitohaina (2) , Natalia Grabar (3) , Fleur Mougin (1) , Thierry Hamon (2, 4)

1 BPH - Bordeaux population health
2 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur
3 STL - Savoirs, Textes, Langage (STL) - UMR 8163
4 UP13 - Université Paris 13

In this paper, we address the problem of automatically constructing a relevant corpus of scientific articles about food-drug interactions. There is a growing number of scientific publications that describe food-drug interactions but currently building a high-coverage corpus that can be used for information extraction purposes is not trivial. We investigate several methods for automating the query selection process using an expert-curated corpus of food-drug interactions. Our experiments show that index term features along with a decision tree classifier are the best approach for this task and that feature selection approaches and in particular gain ratio outperform frequency-based methods for query selection.

Mots clés: Query selection; Corpus construction; Food-drug interactions

Domaines: Informatique [cs]; Informatique et langage [cs.CL]

Georgeta Bordea, Tsanta Randriatsitohaina, Natalia Grabar, Fleur Mougin, Thierry Hamon. Query selection methods for automated corpora construction with a use case in food-drug interactions. ACL Workshop on Biomedical Natural Language Processing, Aug 2019, Florence, Italy. pp.115-124, ⟨10.18653/v1/W19-5013⟩. ⟨hal-02371207⟩