@inproceedings{jain-etal-2026-rating,
title = "Rating Plausibility of Word Senses in Ambiguous Sentences Using Multi-Architecture Analysis",
author = "Jain, Naina and
Arora, Nidhi and
Thakkar, Pal and
Sahu, Siba",
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-1.292/",
pages = "2307--2313",
ISBN = "979-8-89176-414-9",
abstract = "Word sense disambiguation in narrative contexts requires systems to reason about subtle semantic relationships between candidate senses and discourse context. This paper addresses SemEval 2026 Task 5, which reformulates WSD as a graded plausibility prediction problem on a 1{--}5 Likert scale using the AmbiStory dataset. We present two complementary approaches: (1) a DeBERTa-v3-Large encoder with attention-weighted pooling and ordinal regression, achieving a Spearman correlation of 0.718, and (2) a rank-based ensemble combining FLAN-T5 and RoBERTa, achieving 0.692. Through ablation studies, we show that explicitly modeling ordinal structure improves performance over standard regression by 17.3{\%}. We further analyze the strengths of each approach, showing that fine-tuned encoders capture fine-grained semantic relationships, while ensemble methods provide robustness through complementary modeling biases. Our results provide a detailed empirical analysis of design choices for graded plausibility prediction in narrative understanding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jain-etal-2026-rating">
<titleInfo>
<title>Rating Plausibility of Word Senses in Ambiguous Sentences Using Multi-Architecture Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Naina</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nidhi</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pal</namePart>
<namePart type="family">Thakkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siba</namePart>
<namePart type="family">Sahu</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>Word sense disambiguation in narrative contexts requires systems to reason about subtle semantic relationships between candidate senses and discourse context. This paper addresses SemEval 2026 Task 5, which reformulates WSD as a graded plausibility prediction problem on a 1–5 Likert scale using the AmbiStory dataset. We present two complementary approaches: (1) a DeBERTa-v3-Large encoder with attention-weighted pooling and ordinal regression, achieving a Spearman correlation of 0.718, and (2) a rank-based ensemble combining FLAN-T5 and RoBERTa, achieving 0.692. Through ablation studies, we show that explicitly modeling ordinal structure improves performance over standard regression by 17.3%. We further analyze the strengths of each approach, showing that fine-tuned encoders capture fine-grained semantic relationships, while ensemble methods provide robustness through complementary modeling biases. Our results provide a detailed empirical analysis of design choices for graded plausibility prediction in narrative understanding.</abstract>
<identifier type="citekey">jain-etal-2026-rating</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.292/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2307</start>
<end>2313</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rating Plausibility of Word Senses in Ambiguous Sentences Using Multi-Architecture Analysis
%A Jain, Naina
%A Arora, Nidhi
%A Thakkar, Pal
%A Sahu, Siba
%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 jain-etal-2026-rating
%X Word sense disambiguation in narrative contexts requires systems to reason about subtle semantic relationships between candidate senses and discourse context. This paper addresses SemEval 2026 Task 5, which reformulates WSD as a graded plausibility prediction problem on a 1–5 Likert scale using the AmbiStory dataset. We present two complementary approaches: (1) a DeBERTa-v3-Large encoder with attention-weighted pooling and ordinal regression, achieving a Spearman correlation of 0.718, and (2) a rank-based ensemble combining FLAN-T5 and RoBERTa, achieving 0.692. Through ablation studies, we show that explicitly modeling ordinal structure improves performance over standard regression by 17.3%. We further analyze the strengths of each approach, showing that fine-tuned encoders capture fine-grained semantic relationships, while ensemble methods provide robustness through complementary modeling biases. Our results provide a detailed empirical analysis of design choices for graded plausibility prediction in narrative understanding.
%U https://aclanthology.org/2026.semeval-1.292/
%P 2307-2313
Markdown (Informal)
[Rating Plausibility of Word Senses in Ambiguous Sentences Using Multi-Architecture Analysis](https://aclanthology.org/2026.semeval-1.292/) (Jain et al., SemEval 2026)
ACL