@inproceedings{bernal-beltran-etal-2026-umuteam,
title = "{UMUT}eam at {S}em{E}val-2026 Task 6: Soft-Voting Transformer Ensembles for Detecting and Classifying Response Ambiguity in Political Discourse",
author = "Bernal-Beltr{\'a}n, Tom{\'a}s and
Pan, Ronghao and
G{\'o}mez-Naval{\'o}n, Jorge and
Garc{\'i}a-D{\'i}az, Jos{\'e} Antonio and
Valencia-Garcia, Rafael",
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-1.68/",
pages = "475--482",
ISBN = "979-8-89176-414-9",
abstract = "Political discourse frequently involves strategically ambiguous responses, particularly in high-stakes settings such as presidential debates and interviews. Detecting whether a politician has directly answered a question, provided an ambiguous reply or issued a clear non-reply remains a challenging task due to the pragmatic and rhetorical nature of political language. This paper describes our participation in the SemEval 2026 CLARITY shared task on response ambiguity detection and classification in English. We focused exclusively on Task 1 (Clarity-level Classification) and proposed a weighted soft-voting ensemble that combines four fine-tuned encoder-only transformer models: RoBERTa-large, BERT-large-cased, DistilBERT-cased and ModernBERT-large. Each model was optimized through grid search and their predicted class probability distributions were aggregated using a weighted linear combination. On the official test set, our system achieved a macro-F1 score of 0.71, ranking 26th out of 41 participating teams. Even with the performance gap compared to top-ranked systems, our results demonstrate that a lightweight set of moderately sized encoder models can provide stable and competitive performance without relying on external data or large-scale architectures."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bernal-beltran-etal-2026-umuteam">
<titleInfo>
<title>UMUTeam at SemEval-2026 Task 6: Soft-Voting Transformer Ensembles for Detecting and Classifying Response Ambiguity in Political Discourse</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomás</namePart>
<namePart type="family">Bernal-Beltrán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronghao</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Gómez-Navalón</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">Antonio</namePart>
<namePart type="family">García-Díaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Valencia-Garcia</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>Political discourse frequently involves strategically ambiguous responses, particularly in high-stakes settings such as presidential debates and interviews. Detecting whether a politician has directly answered a question, provided an ambiguous reply or issued a clear non-reply remains a challenging task due to the pragmatic and rhetorical nature of political language. This paper describes our participation in the SemEval 2026 CLARITY shared task on response ambiguity detection and classification in English. We focused exclusively on Task 1 (Clarity-level Classification) and proposed a weighted soft-voting ensemble that combines four fine-tuned encoder-only transformer models: RoBERTa-large, BERT-large-cased, DistilBERT-cased and ModernBERT-large. Each model was optimized through grid search and their predicted class probability distributions were aggregated using a weighted linear combination. On the official test set, our system achieved a macro-F1 score of 0.71, ranking 26th out of 41 participating teams. Even with the performance gap compared to top-ranked systems, our results demonstrate that a lightweight set of moderately sized encoder models can provide stable and competitive performance without relying on external data or large-scale architectures.</abstract>
<identifier type="citekey">bernal-beltran-etal-2026-umuteam</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.68/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>475</start>
<end>482</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UMUTeam at SemEval-2026 Task 6: Soft-Voting Transformer Ensembles for Detecting and Classifying Response Ambiguity in Political Discourse
%A Bernal-Beltrán, Tomás
%A Pan, Ronghao
%A Gómez-Navalón, Jorge
%A García-Díaz, José Antonio
%A Valencia-Garcia, Rafael
%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 bernal-beltran-etal-2026-umuteam
%X Political discourse frequently involves strategically ambiguous responses, particularly in high-stakes settings such as presidential debates and interviews. Detecting whether a politician has directly answered a question, provided an ambiguous reply or issued a clear non-reply remains a challenging task due to the pragmatic and rhetorical nature of political language. This paper describes our participation in the SemEval 2026 CLARITY shared task on response ambiguity detection and classification in English. We focused exclusively on Task 1 (Clarity-level Classification) and proposed a weighted soft-voting ensemble that combines four fine-tuned encoder-only transformer models: RoBERTa-large, BERT-large-cased, DistilBERT-cased and ModernBERT-large. Each model was optimized through grid search and their predicted class probability distributions were aggregated using a weighted linear combination. On the official test set, our system achieved a macro-F1 score of 0.71, ranking 26th out of 41 participating teams. Even with the performance gap compared to top-ranked systems, our results demonstrate that a lightweight set of moderately sized encoder models can provide stable and competitive performance without relying on external data or large-scale architectures.
%U https://aclanthology.org/2026.semeval-1.68/
%P 475-482
Markdown (Informal)
[UMUTeam at SemEval-2026 Task 6: Soft-Voting Transformer Ensembles for Detecting and Classifying Response Ambiguity in Political Discourse](https://aclanthology.org/2026.semeval-1.68/) (Bernal-Beltrán et al., SemEval 2026)
ACL