El-Kawaref at WojoodNER shared task: StagedNER for Arabic Named Entity Recognition
Nehal Elkaref, Mohab Elkaref · 2023
Named Entity Recognition (NER) is the task of identifying word-units that correspond to mentions as location, organization, person, or currency.In this shared task (Jarrar et al., 2023) we tackle flat-entity classification for Arabic, where for each word-unit a single entity should be identified.To resolve the classification problem we apply StagedNER as proposed by (Elkaref et al., 2023), which involves fine-tuning NER downstream tasks that divides the learning process of a transformer-model into two phases, where a model is tasked to learn sequence tags and then entity tags rather than learn both together simultaneously for an input sequence.We create an ensemble of two base models using this method that yield a score of F1 performance of 90.03% on the validation set and 91.95% on the test.The submitted model has ranked second for its F1 score, fourth in precision and ranked first scoring the highest recall.