TEAM: A multitask learning based Taxonomy Expansion approach for Attach and Merge
Bornali Phukon, Anasua Mitra, Ranbir Singh Sanasam, Priyankoo Sarmah · Findings of the Association for Computational Linguistics: NAACL 2022 · 2022
Taxonomy expansion is a crucial task.Most of the taxonomy expansion approaches are of two types, attach and merge.In a taxonomy like WordNet, both merge and attach are integral parts of the expansion operations, but the majority of studies consider them separately.This paper proposes a novel multi-task learning-based deep learning method known as Taxonomy Expansion with Attach and Merge (TEAM) that performs both the merge and attach operations.This is the first study that integrates both the merge and attach operations in a single model to the best of our knowledge.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.* Equal contributions.Object (d, s) Rock, Stone (d, s) Food (d, s) Fruit (d, s) Vegetable, Veggie (d, s) Query Anchor Label Operation Rock(d, "rock") Object (d, s) True Attach Rock(d, "rock") Fruit (d,s) False Rock(d, "rock") Stone (parallel_d, s) True Merge Rock(d, "rock") Fruit(d, s) False Concept is a tuple of definition, synset(d, s) Fruit (s) The ripened reproductive body of a seed plant.(d)Vegetable, Veggie (s)