@inproceedings{ravikiran-etal-2026-hi,
title = "Hi-{SEMFLOW}: Lie Algebra{--}Based Semantic Flow for Span-Level Informal Language Identification in {H}indi",
author = "Ravikiran, Manikandan and
Tiwari, Tanmay and
Gupta, Vibhu and
Saluja, Rohit",
editor = "Sarveswaran, Kengatharaiyer and
Vaidya, Ashwini",
booktitle = "Proceedings of the Second workshop on Challenges in Processing {S}outh {A}sian Languages ({CH}i{PSAL}2026)",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.chipsal-1.14/",
doi = "10.63317/2duxp4m72ddj",
pages = "137--153",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ravikiran-etal-2026-hi">
<titleInfo>
<title>Hi-SEMFLOW: Lie Algebra–Based Semantic Flow for Span-Level Informal Language Identification in Hindi</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manikandan</namePart>
<namePart type="family">Ravikiran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmay</namePart>
<namePart type="family">Tiwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vibhu</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohit</namePart>
<namePart type="family">Saluja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kengatharaiyer</namePart>
<namePart type="family">Sarveswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwini</namePart>
<namePart type="family">Vaidya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">ravikiran-etal-2026-hi</identifier>
<identifier type="doi">10.63317/2duxp4m72ddj</identifier>
<location>
<url>https://aclanthology.org/2026.chipsal-1.14/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>137</start>
<end>153</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hi-SEMFLOW: Lie Algebra–Based Semantic Flow for Span-Level Informal Language Identification in Hindi
%A Ravikiran, Manikandan
%A Tiwari, Tanmay
%A Gupta, Vibhu
%A Saluja, Rohit
%Y Sarveswaran, Kengatharaiyer
%Y Vaidya, Ashwini
%S Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F ravikiran-etal-2026-hi
%X 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.
%R 10.63317/2duxp4m72ddj
%U https://aclanthology.org/2026.chipsal-1.14/
%U https://doi.org/10.63317/2duxp4m72ddj
%P 137-153
Markdown (Informal)
[Hi-SEMFLOW: Lie Algebra–Based Semantic Flow for Span-Level Informal Language Identification in Hindi](https://aclanthology.org/2026.chipsal-1.14/) (Ravikiran et al., CHiPSAL 2026)
ACL