@inproceedings{singhal-etal-2026-blue,
title = "blue at {S}em{E}val-2026 Task 5: {N}arr{BERT} : Narrative-Aware {BERT} for Word Sense Disambiguation",
author = "Singhal, Rhea and
Sharma, Krish and
Sharma, Lakksh and
Bedi, Jatin",
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-1.306/",
pages = "2427--2431",
ISBN = "979-8-89176-414-9",
abstract = "This paper outlines the method submitted by team blue for the SemEval-2026 Task 5: Rating Plausibility of Word Senses in Ambiguous Sentences through Narrative (AmbiStory). The task requires predicting reasonable scores that match human thoughts and judgments instead of just picking a single correct sense as the output. This means that contextual reasoning with fine-grain contextual modeling is vital. In order to tackle this problem, we suggest a BERT-based cross-encoder regression model. This model encodes the entire narrative context, which includes the precontext, the ambiguous sentence, and the ending, along with candidate sense definitions and example usages. Unlike bi-encoder sentence-level methods, our model allows for token-level interaction between story cues and sense meanings. This interaction helps capture subtle narrative disambiguation signals. We conduct a systematic exploration of model architectures and training strategies, progressing from a sentence-transformer baseline to an optimised BERT cross-encoder. On the development set, our best configuration achieves a Spearman rank correlation of 0.66. On the official test set, the system achieves a Spearman correlation of 0.4866 and an Accuracy-within-Standard-Deviation of 0.6613, substantially outperforming sentence-transformer bi-encoder baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singhal-etal-2026-blue">
<titleInfo>
<title>blue at SemEval-2026 Task 5: NarrBERT : Narrative-Aware BERT for Word Sense Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rhea</namePart>
<namePart type="family">Singhal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krish</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lakksh</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jatin</namePart>
<namePart type="family">Bedi</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>This paper outlines the method submitted by team blue for the SemEval-2026 Task 5: Rating Plausibility of Word Senses in Ambiguous Sentences through Narrative (AmbiStory). The task requires predicting reasonable scores that match human thoughts and judgments instead of just picking a single correct sense as the output. This means that contextual reasoning with fine-grain contextual modeling is vital. In order to tackle this problem, we suggest a BERT-based cross-encoder regression model. This model encodes the entire narrative context, which includes the precontext, the ambiguous sentence, and the ending, along with candidate sense definitions and example usages. Unlike bi-encoder sentence-level methods, our model allows for token-level interaction between story cues and sense meanings. This interaction helps capture subtle narrative disambiguation signals. We conduct a systematic exploration of model architectures and training strategies, progressing from a sentence-transformer baseline to an optimised BERT cross-encoder. On the development set, our best configuration achieves a Spearman rank correlation of 0.66. On the official test set, the system achieves a Spearman correlation of 0.4866 and an Accuracy-within-Standard-Deviation of 0.6613, substantially outperforming sentence-transformer bi-encoder baselines.</abstract>
<identifier type="citekey">singhal-etal-2026-blue</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.306/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2427</start>
<end>2431</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T blue at SemEval-2026 Task 5: NarrBERT : Narrative-Aware BERT for Word Sense Disambiguation
%A Singhal, Rhea
%A Sharma, Krish
%A Sharma, Lakksh
%A Bedi, Jatin
%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 singhal-etal-2026-blue
%X This paper outlines the method submitted by team blue for the SemEval-2026 Task 5: Rating Plausibility of Word Senses in Ambiguous Sentences through Narrative (AmbiStory). The task requires predicting reasonable scores that match human thoughts and judgments instead of just picking a single correct sense as the output. This means that contextual reasoning with fine-grain contextual modeling is vital. In order to tackle this problem, we suggest a BERT-based cross-encoder regression model. This model encodes the entire narrative context, which includes the precontext, the ambiguous sentence, and the ending, along with candidate sense definitions and example usages. Unlike bi-encoder sentence-level methods, our model allows for token-level interaction between story cues and sense meanings. This interaction helps capture subtle narrative disambiguation signals. We conduct a systematic exploration of model architectures and training strategies, progressing from a sentence-transformer baseline to an optimised BERT cross-encoder. On the development set, our best configuration achieves a Spearman rank correlation of 0.66. On the official test set, the system achieves a Spearman correlation of 0.4866 and an Accuracy-within-Standard-Deviation of 0.6613, substantially outperforming sentence-transformer bi-encoder baselines.
%U https://aclanthology.org/2026.semeval-1.306/
%P 2427-2431
Markdown (Informal)
[blue at SemEval-2026 Task 5: NarrBERT : Narrative-Aware BERT for Word Sense Disambiguation](https://aclanthology.org/2026.semeval-1.306/) (Singhal et al., SemEval 2026)
ACL