@inproceedings{faisal-etal-2026-context,
title = "{C}on{T}ex{T} at {S}em{E}val-2026 Task 5: Rating Plausibility of Word Senses in Ambiguous Stories through Narrative Understanding",
author = "Faisal, Fakeha and
Shah, Rubab and
Zaidi, Syeda and
Nasir, Azkaa and
Kumar, Sandesh and
Samad, Abdul",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.232/",
pages = "1840--1845",
ISBN = "979-8-89176-414-9",
abstract = "In this paper, we report our system for SemEval-2026 Task 5, which predicts graded plausibility scores for target word senses in narrative context. We explore embedding-based similarity, transformer fine tuning, and a three-stage curriculum combining WiC pretraining, Wasserstein distribution learning, and KL-based calibration. Our best model, DeBERTa-XLarge with curriculum training, achieves 78{\%} accu-racy within one standard deviation and a Spear-man correlation of 0.70, with an overall test score of 0.74. Results show that distribution modeling better aligns with human plausibility judgments than single-score prediction"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="faisal-etal-2026-context">
<titleInfo>
<title>ConTexT at SemEval-2026 Task 5: Rating Plausibility of Word Senses in Ambiguous Stories through Narrative Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fakeha</namePart>
<namePart type="family">Faisal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rubab</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syeda</namePart>
<namePart type="family">Zaidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azkaa</namePart>
<namePart type="family">Nasir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdul</namePart>
<namePart type="family">Samad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>In this paper, we report our system for SemEval-2026 Task 5, which predicts graded plausibility scores for target word senses in narrative context. We explore embedding-based similarity, transformer fine tuning, and a three-stage curriculum combining WiC pretraining, Wasserstein distribution learning, and KL-based calibration. Our best model, DeBERTa-XLarge with curriculum training, achieves 78% accu-racy within one standard deviation and a Spear-man correlation of 0.70, with an overall test score of 0.74. Results show that distribution modeling better aligns with human plausibility judgments than single-score prediction</abstract>
<identifier type="citekey">faisal-etal-2026-context</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.232/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1840</start>
<end>1845</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ConTexT at SemEval-2026 Task 5: Rating Plausibility of Word Senses in Ambiguous Stories through Narrative Understanding
%A Faisal, Fakeha
%A Shah, Rubab
%A Zaidi, Syeda
%A Nasir, Azkaa
%A Kumar, Sandesh
%A Samad, Abdul
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F faisal-etal-2026-context
%X In this paper, we report our system for SemEval-2026 Task 5, which predicts graded plausibility scores for target word senses in narrative context. We explore embedding-based similarity, transformer fine tuning, and a three-stage curriculum combining WiC pretraining, Wasserstein distribution learning, and KL-based calibration. Our best model, DeBERTa-XLarge with curriculum training, achieves 78% accu-racy within one standard deviation and a Spear-man correlation of 0.70, with an overall test score of 0.74. Results show that distribution modeling better aligns with human plausibility judgments than single-score prediction
%U https://aclanthology.org/2026.semeval-1.232/
%P 1840-1845
Markdown (Informal)
[ConTexT at SemEval-2026 Task 5: Rating Plausibility of Word Senses in Ambiguous Stories through Narrative Understanding](https://aclanthology.org/2026.semeval-1.232/) (Faisal et al., SemEval 2026)
ACL