Hidden Markov Based Mathematical Model dedicated to Extract Ingredients from Recipe Text

Zied Baklouti (1, 2)

1 UPCité - Université Paris Cité
2 ENIT - Ecole Nationale d'Ingénieurs de Tunis

Natural Language Processing (NLP) is a branch of artificial intelligence that gives machines the ability to decode human languages. Partof-speech tagging (POS tagging) is a pre-processing task that requires an annotated corpus. Rule-based and stochastic methods showed remarkable results for POS tag prediction. On this work, I performed a mathematical model based on Hidden Markov structures and I obtained a high-level accuracy of ingredients extracted from text recipe with performances greater than what traditional methods could make without unknown words consideration.

Domaines: Informatique; Intelligence artificielle [cs.AI]

Zied Baklouti. Hidden Markov Based Mathematical Model dedicated to Extract Ingredients from Recipe Text. 2021. ⟨hal-03355929⟩