Artikel in einem Konferenzbericht,
Fine-tuned BERT Model for Multi-Label Tweets Classification
Proceedings of the Twenty-Eighth Text REtrieval Conference, TREC 2019, Gaithersburg, Maryland, USA, November 13-15, 2019, (2019)
Zusammenfassung
In this paper, we describe our approach to classify disaster-related tweets into multilabel information types (ie, labels). We aim to filter first relevant tweets during disasters. Then, we assign tweets relevant information types. Information types can be SearchAndRescue, MovePeople and Volunteer. We employ a fine-tuned BERT model with 10 BERT layers. Further, we submitted our approach to the TREC-IS 2019 challenge, the evaluation results showed that our approach outperforms the F1-score of median score in identifying actionable information.
