DepNeCTI: Dependency-based Nested Compound Type Identification for Sanskrit
This work addresses a gap in lexical semantics for Sanskrit by focusing on multi-component compounds, which is incremental as it builds on prior binary compound identification methods.
The paper tackles the problem of identifying nested spans and semantic relations in multi-component Sanskrit compounds, introducing the novel task of nested compound type identification (NeCTI) and presenting a dependency-based framework (DepNeCTI) that achieves an average absolute improvement of 13.1 points F1-score in Labeled Span Score and a 5-fold enhancement in inference efficiency over baselines.
Multi-component compounding is a prevalent phenomenon in Sanskrit, and understanding the implicit structure of a compound's components is crucial for deciphering its meaning. Earlier approaches in Sanskrit have focused on binary compounds and neglected the multi-component compound setting. This work introduces the novel task of nested compound type identification (NeCTI), which aims to identify nested spans of a multi-component compound and decode the implicit semantic relations between them. To the best of our knowledge, this is the first attempt in the field of lexical semantics to propose this task. We present 2 newly annotated datasets including an out-of-domain dataset for this task. We also benchmark these datasets by exploring the efficacy of the standard problem formulations such as nested named entity recognition, constituency parsing and seq2seq, etc. We present a novel framework named DepNeCTI: Dependency-based Nested Compound Type Identifier that surpasses the performance of the best baseline with an average absolute improvement of 13.1 points F1-score in terms of Labeled Span Score (LSS) and a 5-fold enhancement in inference efficiency. In line with the previous findings in the binary Sanskrit compound identification task, context provides benefits for the NeCTI task. The codebase and datasets are publicly available at: https://github.com/yaswanth-iitkgp/DepNeCTI