Work

Dual-Axis Compositional Contrastive Few-Shot Learning using Prototypes Across Linguistic and Semantic Dimensions for Indic Low-Resource Multilingual NLU

Year: 2026

Type: conference-paper

Abstract: Multilingual Natural Language Understanding (NLU) systems often struggle to adapt when new languages or new semantic labels are introduced with only a few annotated examples.This challenge is particularly pronounced for low-resource languages, where limited supervision and evolving label spaces make conventional joint-label classification approaches unstable.Most existing multilingual NLU models treat each language-semantic pair as an independent class, entangling linguistic and semantic representations and hindering few-shot adaptation.We propose Dual-Axis Compositional Few-Shot Learning, a framework that explicitly factorizes the representation space into linguistic and semantic embedding axes, enabling independent modeling of language variation and domain-intent semantics.Joint representations are constructed compositionally through multiplicative interaction of axis-specific embeddings, allowing controlled adaptation when either the language set or the semantic label space evolves.The framework integrates factorized prototype learning, axis-structured contrastive alignment, and disentanglement regularization using HSIC-based statistical independence and Jacobian-based cross-axis decorrelation.Experiments on six low-resource Indic languages spanning Indo-Aryan and Dravidian families (Hindi, Bengali, Sanskrit, Assamese, Tamil, and Telugu) demonstrate strong performance under two structured generalization regimes.The model achieves 81.12% accuracy when adapting to few-shot languages with known semantics and 63.5% accuracy when learning new semantic classes from few-shot examples, along with an accuracy of 89.56% on known languages and seen semantics.These results show that axis-factorized representations enable stable compositional generalization, offering a promising direction for scalable multilingual NLU in linguistically diverse low-resource settings.

Source: Workshop on Language Technology for Equality, Diversity, Inclusion (LT-EDI)

DOI: 10.18653/v1/2026.ltedi-1.3

Authors: Kathakali Mitra, Sakshi Singh, Sree Nithish Reddy Gunapati, Aruna Malapati, Mark G. Lee

Institutions: Birla Institute of Technology and Science - Hyderabad Campus, Birla Institute of Technology and Science, Pilani, University of Birmingham

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W7166827456

FWCI:

Cites:

Cited by:

Related to: 10