Hi-SEMFLOW: Lie Algebra–Based Semantic Flow for Span-Level Informal Language Identification in Hindi

Manikandan Ravikiran, Tanmay Tiwari, Vibhu Gupta, Rohit Saluja


Abstract
Informal Hindi text frequently contains multi-token slang and idiomatic expressions whose correct identification requires consistent span boundaries. Transformer-based token classifiers, despite strong contextual representations, often produce fragmented or structurally invalid BIO sequences due to largely local predictions. We propose Hi-SEMFLOW, a Lie algebra–based semantic flow framework that models span consistency as a continuous refinement process over label logits. Instead of discrete structured decoding (e.g., CRFs), Hi-SEMFLOW learns context-dependent transition operators derived from antisymmetric generators and propagates structural information through smooth, fully differentiable transformations. This formulation integrates structural bias directly into end-to-end training without requiring dynamic programming or hard decoding constraints. Experiments on the HiSlang-4.9k benchmark show that Hi-SEMFLOW improves span-level F1 by up to 2–3 absolute points and yields consistent macro-F1 gains across Hindi-pretrained encoders. Extensive ablations demonstrate that continuous geometric refinement provides a flexible and effective alternative to discrete structured decoding for span-centric sequence labeling.
Anthology ID:
2026.chipsal-1.14
Volume:
Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Kengatharaiyer Sarveswaran, Ashwini Vaidya
Venues:
CHiPSAL | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
137–153
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-chipsal-14
DOI:
10.63317/2duxp4m72ddj
Bibkey:
Cite (ACL):
Manikandan Ravikiran, Tanmay Tiwari, Vibhu Gupta, and Rohit Saluja. 2026. Hi-SEMFLOW: Lie Algebra–Based Semantic Flow for Span-Level Informal Language Identification in Hindi. In Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026), pages 137–153, Palma de Mallorca, Spain. ELRA Language Resources Association (ELRA).
Cite (Informal):
Hi-SEMFLOW: Lie Algebra–Based Semantic Flow for Span-Level Informal Language Identification in Hindi (Ravikiran et al., CHiPSAL 2026)
Copy Citation: