@inproceedings{hsieh-etal-2026-nycu,
title = "{NYCU} Speech Lab at {S}em{E}val-2026 Task 3: Heterogeneous Model Ensemble with Adaptive Weighted Voting for Dimensional Aspect Sentiment Quadruplet Extraction",
author = "Hsieh, Hao-Chun and
Wu, Cheng-En and
Liao, Yuan-Fu",
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-1.203/",
pages = "1568--1574",
ISBN = "979-8-89176-414-9",
abstract = "SemEval-2026 Task 3 (DimABSA) includes Dimensional Aspect Sentiment Quadruplet Extraction (DimASQP), which requires extracting structured tuples{---}aspect term, aspect category, and opinion term{---}together with continuous valence{--}arousal (VA) values from reviews (Yu et al., 2026a). In this work, we participate in Track A, Subtask 3. We describe NYCU Speech Lab{'}s submission for the Chinese Restaurant and Laptop domains. Our system is a post-processing ensemble over heterogeneous architectures: LoRA/QLoRA fine-tuned decoder-only LLMs, a fine-tuned encoder-only model, and (optionally) prompted API-based LLMs. To improve robustness under the continuous F1 (cF1) metric, we use validation-calibrated weighted voting for tuple selection and weighted VA fusion for numerical aggregation, with strict output validation to enforce task constraints. Experiments on a held-out validation split show consistent gains over single models and clarify the precision{--}recall trade-offs induced by the voting threshold. On the organizers' released (tentative) test leaderboard snapshot, our submission ranks first in both domains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hsieh-etal-2026-nycu">
<titleInfo>
<title>NYCU Speech Lab at SemEval-2026 Task 3: Heterogeneous Model Ensemble with Adaptive Weighted Voting for Dimensional Aspect Sentiment Quadruplet Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao-Chun</namePart>
<namePart type="family">Hsieh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng-En</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan-Fu</namePart>
<namePart type="family">Liao</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>SemEval-2026 Task 3 (DimABSA) includes Dimensional Aspect Sentiment Quadruplet Extraction (DimASQP), which requires extracting structured tuples—aspect term, aspect category, and opinion term—together with continuous valence–arousal (VA) values from reviews (Yu et al., 2026a). In this work, we participate in Track A, Subtask 3. We describe NYCU Speech Lab’s submission for the Chinese Restaurant and Laptop domains. Our system is a post-processing ensemble over heterogeneous architectures: LoRA/QLoRA fine-tuned decoder-only LLMs, a fine-tuned encoder-only model, and (optionally) prompted API-based LLMs. To improve robustness under the continuous F1 (cF1) metric, we use validation-calibrated weighted voting for tuple selection and weighted VA fusion for numerical aggregation, with strict output validation to enforce task constraints. Experiments on a held-out validation split show consistent gains over single models and clarify the precision–recall trade-offs induced by the voting threshold. On the organizers’ released (tentative) test leaderboard snapshot, our submission ranks first in both domains.</abstract>
<identifier type="citekey">hsieh-etal-2026-nycu</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.203/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1568</start>
<end>1574</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NYCU Speech Lab at SemEval-2026 Task 3: Heterogeneous Model Ensemble with Adaptive Weighted Voting for Dimensional Aspect Sentiment Quadruplet Extraction
%A Hsieh, Hao-Chun
%A Wu, Cheng-En
%A Liao, Yuan-Fu
%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 hsieh-etal-2026-nycu
%X SemEval-2026 Task 3 (DimABSA) includes Dimensional Aspect Sentiment Quadruplet Extraction (DimASQP), which requires extracting structured tuples—aspect term, aspect category, and opinion term—together with continuous valence–arousal (VA) values from reviews (Yu et al., 2026a). In this work, we participate in Track A, Subtask 3. We describe NYCU Speech Lab’s submission for the Chinese Restaurant and Laptop domains. Our system is a post-processing ensemble over heterogeneous architectures: LoRA/QLoRA fine-tuned decoder-only LLMs, a fine-tuned encoder-only model, and (optionally) prompted API-based LLMs. To improve robustness under the continuous F1 (cF1) metric, we use validation-calibrated weighted voting for tuple selection and weighted VA fusion for numerical aggregation, with strict output validation to enforce task constraints. Experiments on a held-out validation split show consistent gains over single models and clarify the precision–recall trade-offs induced by the voting threshold. On the organizers’ released (tentative) test leaderboard snapshot, our submission ranks first in both domains.
%U https://aclanthology.org/2026.semeval-1.203/
%P 1568-1574
Markdown (Informal)
[NYCU Speech Lab at SemEval-2026 Task 3: Heterogeneous Model Ensemble with Adaptive Weighted Voting for Dimensional Aspect Sentiment Quadruplet Extraction](https://aclanthology.org/2026.semeval-1.203/) (Hsieh et al., SemEval 2026)
ACL