SubmissionNumber#=%=#19
FinalPaperTitle#=%=#AdaBioBERT: Adaptive Token Sequence Learning for Biomedical Named Entity Recognition
ShortPaperTitle#=%=#
NumberOfPages#=%=#7
CopyrightSigned#=%=#Sumit Kumar
JobTitle#==#
Organization#==#Indian Institute of Science Education and Research Bhopal, Madhya Pradesh, India
Abstract#==#Accurate identification and labeling of biomedical entities, such as diseases, genes, chemical and species, within scientific texts are crucial for understanding complex relationships. We propose Adaptive BERT or AdaBioBERT, a robust named entity recognition (NER) model that builds upon BioBERT (Biomedical Bidirectional Encoded Representation from Transformers) based on an adaptive loss function to learn different types of biomedical token sequence. This adaptive loss function combines the standard Cross Entropy (CE) loss and Conditional Random Field (CRF) loss to optimize both token level accuracy and sequence-level coherence. AdaBioBERT captures rich semantic nuances by leveraging pre-trained contextual embeddings from BioBERT. On the other hand, the CRF loss of AdaBioBERT ensures proper identification of complex  multi-token biomedical entities in a sequence and the CE loss can capture the simple unigram entities in a sequence. The empirical analysis on multiple standard biomedical coprora demonstrates that AdaBioBERT performs better than the state of the arts for most of the datasets in terms of macro and micro averaged F1 score.
Author{1}{Firstname}#=%=#Sumit
Author{1}{Lastname}#=%=#Kumar
Author{1}{Username}#=%=#sumitkumar9297
Author{1}{Email}#=%=#sumit23@iiserb.ac.in
Author{1}{Affiliation}#=%=#Indian Institute of Science Education and Research Bhopal
Author{2}{Firstname}#=%=#Tanmay
Author{2}{Lastname}#=%=#Basu
Author{2}{Username}#=%=#tanmaybasu
Author{2}{Email}#=%=#welcometanmay@gmail.com
Author{2}{Affiliation}#=%=#Indian Institute of Science Education and Research Bhopal

==========
èéáğö