@inproceedings{varanasi-etal-2026-signsim,
title = "{S}ign{S}im: A Landmark Driven Model for Phonological Sign Similarity Prediction",
author = "Varanasi, Abhishek Bharadwaj and
Sinha, Manjira and
Dasgupta, Tirthankar and
Jadhav, Dr. Charudatta",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.72/",
pages = "1412--1424",
ISBN = "979-8-89176-444-6",
abstract = "Phonological similarity is fundamental to sign language structure and cross-linguistic analysis, yet existing approaches based on HamNoSys operate only at the transcription level and ignore visual realization. We propose a phonology-aware model that predicts continuous phonological similarity directly from sign videos while remaining grounded in symbolic phonological structure. Our landmark-based approach uses body and hand keypoints extracted with MediaPipe and a temporal encoder combining short-term convolution with Head-Token Mixing Attention to capture both local articulation and long-range dynamics. By factorizing HamNoSys annotations into interpretable phonological components and using them as auxiliary supervision, the model learns robust and interpretable representations. Experiments on four sign languages show consistent improvements over alignment-based and RGB-based baselines, particularly in cross-linguistic generalization."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="varanasi-etal-2026-signsim">
<titleInfo>
<title>SignSim: A Landmark Driven Model for Phonological Sign Similarity Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="given">Bharadwaj</namePart>
<namePart type="family">Varanasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manjira</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Dasgupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dr.</namePart>
<namePart type="given">Charudatta</namePart>
<namePart type="family">Jadhav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Phonological similarity is fundamental to sign language structure and cross-linguistic analysis, yet existing approaches based on HamNoSys operate only at the transcription level and ignore visual realization. We propose a phonology-aware model that predicts continuous phonological similarity directly from sign videos while remaining grounded in symbolic phonological structure. Our landmark-based approach uses body and hand keypoints extracted with MediaPipe and a temporal encoder combining short-term convolution with Head-Token Mixing Attention to capture both local articulation and long-range dynamics. By factorizing HamNoSys annotations into interpretable phonological components and using them as auxiliary supervision, the model learns robust and interpretable representations. Experiments on four sign languages show consistent improvements over alignment-based and RGB-based baselines, particularly in cross-linguistic generalization.</abstract>
<identifier type="citekey">varanasi-etal-2026-signsim</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.72/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1412</start>
<end>1424</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SignSim: A Landmark Driven Model for Phonological Sign Similarity Prediction
%A Varanasi, Abhishek Bharadwaj
%A Sinha, Manjira
%A Dasgupta, Tirthankar
%A Jadhav, Dr. Charudatta
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F varanasi-etal-2026-signsim
%X Phonological similarity is fundamental to sign language structure and cross-linguistic analysis, yet existing approaches based on HamNoSys operate only at the transcription level and ignore visual realization. We propose a phonology-aware model that predicts continuous phonological similarity directly from sign videos while remaining grounded in symbolic phonological structure. Our landmark-based approach uses body and hand keypoints extracted with MediaPipe and a temporal encoder combining short-term convolution with Head-Token Mixing Attention to capture both local articulation and long-range dynamics. By factorizing HamNoSys annotations into interpretable phonological components and using them as auxiliary supervision, the model learns robust and interpretable representations. Experiments on four sign languages show consistent improvements over alignment-based and RGB-based baselines, particularly in cross-linguistic generalization.
%U https://aclanthology.org/2026.findings-aacl.72/
%P 1412-1424
Markdown (Informal)
[SignSim: A Landmark Driven Model for Phonological Sign Similarity Prediction](https://aclanthology.org/2026.findings-aacl.72/) (Varanasi et al., Findings 2026)
ACL