EMNLP Findings2021
An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog
Abstract
Online conversations include more than just text. Increasingly, image-based responses such as memes and animated gifs serve as culturally recognized and often humorous responses in conversation. However, while NLP has broadened to multimodal models, conversational dialog systems have largely focused only on generating text replies. Here, we introduce a new dataset of 1.56M text-gif conversation turns and introduce a new multimodal conversational model PEPE THE KING PRAWN for selecting gif-based replies. We demonstrate that our model produces relevant and high-quality gif responses and, in a large randomized control trial of multiple models replying to real users, we show that our model replies with gifs that are significantly better received by the community.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on6
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- CAMP: Cross-Modal Adaptive Message Passing for Text-Image RetrievalZihao Wang, Xihui Liu, Hongsheng Li, Lu Sheng et al.ICCV 2019 · 349 citations
- Few-Shot Conversational Dense RetrievalShi Yu, Zhenghao Liu, Chenyan Xiong, Tao Feng et al.SIGIR 2021 · 75 citations
- Conversational Graph Grounded Policy Learning for Open-Domain Conversation GenerationJun Xu, Haifeng Wang, Zheng-Yu Niu, Hua Wu et al.ACL 2020 · 52 citations
- Multimodal Neural Graph Memory Networks for Visual Question AnsweringMahmoud KhademiACL 2020 · 35 citations
Related papers
- A New Formula for Sticker Retrieval: Reply with Stickers in Multi-Modal and Multi-Session ConversationBingbing Wang, Yiming Du, Bin Liang, Zhixin Bai et al.AAAI 2025 · 5 citations
- MemeCap: A Dataset for Captioning and Interpreting MemesEunjeong Hwang, Vered ShwartzEMNLP 2023 · 14 citations
- PromptMTopic: Unsupervised Multimodal Topic Modeling of Memes using Large Language ModelsNirmalendu Prakash, Han Wang, Nguyen-Khoi Hoang, Ming Shan Hee et al.ACM MM 2023 · 24 citations
- MetaGPT: A Large Vision-Language Model for Meme Metaphor UnderstandingBo Xu, Chenyuan Wang, Xinyu Chen, Hongfei Lin et al.AAAI 2026
- Integrating Stickers into Multimodal Dialogue Summarization: A Novel Dataset and Approach for Enhancing Social Media InteractionYuanchen Shi, Fang KongACM MM 2024 · 7 citations
