Metraipolis › archive › dc_ebaace484e14

S2TDR: Structured Multimodal Reconstruction for Sticker-Aware Dialogue Understanding — arXiv:2610.41176

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41176
License (as archived): CC0-1.0
Archived: 2026-11-02T07:12:37.434Z
SHA-256 of the archived text: f5f3306f9652a161a5ab3a3f4b2ffc3f9049433095a7d8fabd70a6be1eec3bb6
Stable URL of this page: https://metraipolis.com/documento/dc_ebaace484e14

How to cite

S2TDR: Structured Multimodal Reconstruction for Sticker-Aware Dialogue Understanding — arXiv:2610.41176 — arXiv (en), https://arxiv.org/abs/2610.41176 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebaace484e14 (Metraipolis archive dc_ebaace484e14, sha256 f5f3306f9652a161a5ab3a3f4b2ffc3f9049433095a7d8fabd70a6be1eec3bb6)

BibTeX

@misc{dcebaace484e14,
  title = {S2TDR: Structured Multimodal Reconstruction for Sticker-Aware Dialogue Understanding — arXiv:2610.41176},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41176},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebaace484e14; sha256 f5f3306f9652a161a5ab3a3f4b2ffc3f9049433095a7d8fabd70a6be1eec3bb6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41176. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.41176 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-02T07:07:14.189Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).