TY - GEN
T1 - Improving Downstream Task Performance by Treating Numbers as Entities
AU - Sundararaman, Dhanasekar
AU - Subramanian, Vivek
AU - Wang, Guoyin
AU - Xu, Liyan
AU - Carin, Lawrence
N1 - Publisher Copyright:
© 2022 ACM.
PY - 2022/10/17
Y1 - 2022/10/17
N2 - Numbers are essential components of text, like any other word tokens, from which natural language processing (NLP) models are built and deployed. Though numbers are typically not accounted for distinctly in most NLP tasks, there is still an underlying amount of numeracy already exhibited by NLP models. For instance, in named entity recognition (NER), numbers are not treated as an entity with distinct tags. In this work, we attempt to tap the potential of state-of-the-art language models and transfer their ability to boost performance in related downstream tasks dealing with numbers. Our proposed classification of numbers into entities helps NLP models perform well on several tasks, including a handcrafted Fill-In-The-Blank (FITB) task and on question answering, using joint embeddings, outperforming the BERT and RoBERTa baseline classification.
AB - Numbers are essential components of text, like any other word tokens, from which natural language processing (NLP) models are built and deployed. Though numbers are typically not accounted for distinctly in most NLP tasks, there is still an underlying amount of numeracy already exhibited by NLP models. For instance, in named entity recognition (NER), numbers are not treated as an entity with distinct tags. In this work, we attempt to tap the potential of state-of-the-art language models and transfer their ability to boost performance in related downstream tasks dealing with numbers. Our proposed classification of numbers into entities helps NLP models perform well on several tasks, including a handcrafted Fill-In-The-Blank (FITB) task and on question answering, using joint embeddings, outperforming the BERT and RoBERTa baseline classification.
KW - named entity
KW - numeracy
KW - text tagging
UR - http://www.scopus.com/inward/record.url?scp=85140822954&partnerID=8YFLogxK
U2 - 10.1145/3511808.3557614
DO - 10.1145/3511808.3557614
M3 - Conference contribution
AN - SCOPUS:85140822954
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 4535
EP - 4539
BT - CIKM 2022 - Proceedings of the 31st ACM International Conference on Information and Knowledge Management
PB - Association for Computing Machinery
T2 - 31st ACM International Conference on Information and Knowledge Management, CIKM 2022
Y2 - 17 October 2022 through 21 October 2022
ER -