@inproceedings{fu-etal-2026-teleai,
title = "{T}ele{AI} at {S}em{E}val-2026 Task 4: Few-Shot Narrative Similarity Modeling for Classification and Ranking",
author = "Fu, Weiwei and
Wang, Shiquan and
Fang, Ruiyu and
Song, Shuangyong",
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-1.164/",
pages = "1228--1236",
ISBN = "979-8-89176-414-9",
abstract = "This paper presents a unified, task-adaptive modeling framework for the two tracks of SemEval-2026 Task 4: Narrative Similarity. For Track A, we build a three-stage pipeline of three-dimensional narrative-anchored chain-of-thought (CoT) reasoning, multi-view data augmentation, and Low-Rank Adaptation (LoRA) fine-tuning. For Track B, we design an architecture fully aligned with the ranking inference pipeline and task objective, along with corresponding data augmentation and expansion methods, and propose Smooth Cosine Contrastive Loss (SCCL) to stabilize training in low-resource settings. Systematic experiments verify the effectiveness of each core module, and our final systems rank 4th in both tracks, providing a reproducible technical solution for few-shot similarity modeling."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fu-etal-2026-teleai">
<titleInfo>
<title>TeleAI at SemEval-2026 Task 4: Few-Shot Narrative Similarity Modeling for Classification and Ranking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weiwei</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiquan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiyu</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuangyong</namePart>
<namePart type="family">Song</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 presents a unified, task-adaptive modeling framework for the two tracks of SemEval-2026 Task 4: Narrative Similarity. For Track A, we build a three-stage pipeline of three-dimensional narrative-anchored chain-of-thought (CoT) reasoning, multi-view data augmentation, and Low-Rank Adaptation (LoRA) fine-tuning. For Track B, we design an architecture fully aligned with the ranking inference pipeline and task objective, along with corresponding data augmentation and expansion methods, and propose Smooth Cosine Contrastive Loss (SCCL) to stabilize training in low-resource settings. Systematic experiments verify the effectiveness of each core module, and our final systems rank 4th in both tracks, providing a reproducible technical solution for few-shot similarity modeling.</abstract>
<identifier type="citekey">fu-etal-2026-teleai</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.164/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1228</start>
<end>1236</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TeleAI at SemEval-2026 Task 4: Few-Shot Narrative Similarity Modeling for Classification and Ranking
%A Fu, Weiwei
%A Wang, Shiquan
%A Fang, Ruiyu
%A Song, Shuangyong
%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 fu-etal-2026-teleai
%X This paper presents a unified, task-adaptive modeling framework for the two tracks of SemEval-2026 Task 4: Narrative Similarity. For Track A, we build a three-stage pipeline of three-dimensional narrative-anchored chain-of-thought (CoT) reasoning, multi-view data augmentation, and Low-Rank Adaptation (LoRA) fine-tuning. For Track B, we design an architecture fully aligned with the ranking inference pipeline and task objective, along with corresponding data augmentation and expansion methods, and propose Smooth Cosine Contrastive Loss (SCCL) to stabilize training in low-resource settings. Systematic experiments verify the effectiveness of each core module, and our final systems rank 4th in both tracks, providing a reproducible technical solution for few-shot similarity modeling.
%U https://aclanthology.org/2026.semeval-1.164/
%P 1228-1236
Markdown (Informal)
[TeleAI at SemEval-2026 Task 4: Few-Shot Narrative Similarity Modeling for Classification and Ranking](https://aclanthology.org/2026.semeval-1.164/) (Fu et al., SemEval 2026)
ACL