cs.CLOct 30, 2026

S2TDR: Structured Multimodal Reconstruction for Sticker-Aware Dialogue Understanding

Authors: Yuanchen Shi, Fang Kong

Organizations: Natural Language Processing Laboratory, School of Computer Science and Technology, Soochow University, Suzhou, China

Abstract

Stickers are widely used in social media dialogues to express affect, stance, and intent beyond literal text. Their meanings are often non-literal and context-dependent, making them difficult to handle with generic visual fusion or standalone captioning. We propose Sticker-to-Text Dialogue Reconstruction (S2TDR), a structured multimodal reconstruction framework that converts sticker turns into contextually appropriate textual utterances. S2TDR decomposes sticker interpretation into visual cue extraction, affective-intent inference, and context-aware dialogue reconstruction, using OCR text only as an auxiliary cue when available. The reconstructed dialogue can then be consumed by existing text-based dialogue models. Experiments on sentiment analysis, intent recognition, and dialogue summarization show that S2TDR generally improves multiple downstream models over direct sticker integration methods. Further analyses on component ablations, OCR-empty stickers, and reconstruction quality indicate that structured reconstruction provides an interpretable and effective way to integrate sticker semantics into dialogue understanding.

Figures & tables

Explore similar work

CardsList
  1. SEAL: Semantic-aware Single-image Sticker Personalization with a Large-scale Sticker-tag Dataset

    Apr 29, 2026Changhyun Roh, Yonghyun Jeong, Jonghyun Lee +2T2I GenerationIdentity-Preserving Image Generation

  2. S2Dialog: Multimodal Dialogue Retrieval with Semantic and Acoustic-Style Modeling

    Aug 14, 2026Xueqi Wang, Zhigang Wang, Runqing Zhang +2Multimodal IR

  3. GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking

    May 6, 2026Ziqi Zhu, Adithya Suresh, Tomal Deb +1Spoken Dialogue SystemsState Tracking