Bornali Phukon


2022

pdf bib
TEAM: A multitask learning based Taxonomy Expansion approach for Attach and Merge
Bornali Phukon | Anasua Mitra | Ranbir Sanasam | Priyankoo Sarmah
Findings of the Association for Computational Linguistics: NAACL 2022

Taxonomy expansion is a crucial task. Most of Automatic expansion of taxonomy are of two types, attach and merge. In a taxonomy like WordNet, both merge and attach are integral parts of the expansion operations but majority of study consider them separately. This paper proposes a novel mult-task learning-based deep learning method known as Taxonomy Expansion with Attach and Merge (TEAM) that performs both the merge and attach operations. To the best of our knowledge this is the first study which integrates both merge and attach operations in a single model. The proposed models have been evaluated on three separate WordNet taxonomies, viz., Assamese, Bangla, and Hindi. From the various experimental setups, it is shown that TEAM outperforms its state-of-the-art counterparts for attach operation, and also provides highly encouraging performance for the merge operation.