# An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog

arXiv: https://arxiv.org/abs/2109.12212 · HTML: https://mlsanity.com/paper/2109.12212/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 57 references that are in the map.
- First posted on arXiv 24 Sep 2021.

## Builds on (most cited first, 22 of 22)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks](https://mlsanity.com/paper/1711.10485/) (2017)
- [A Tutorial on Thompson Sampling](https://mlsanity.com/paper/1707.02038/) (2017)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [BERTweet: A pre-trained language model for English Tweets](https://mlsanity.com/paper/2005.10200/) (2020)
- [Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models](https://mlsanity.com/paper/1411.2539/) (2014)
- [The Design and Implementation of XiaoIce, an Empathetic Social Chatbot](https://mlsanity.com/paper/1812.08989/) (2018)
- [PP-OCR: A Practical Ultra Lightweight OCR System](https://mlsanity.com/paper/2009.09941/) (2020)
- [Learning Deep Structure-Preserving Image-Text Embeddings](https://mlsanity.com/paper/1511.06078/) (2015)
- [A Knowledge-Grounded Neural Conversation Model](https://mlsanity.com/paper/1702.01932/) (2017)
- [CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval](https://mlsanity.com/paper/1909.05506/) (2019)
- [Few-Shot Conversational Dense Retrieval](https://mlsanity.com/paper/2105.04166/) (2021)
- [Conversational AI: The Science Behind the Alexa Prize](https://mlsanity.com/paper/1801.03604/) (2018)
- [A Network Perspective on Stratification of Multi-Label Data](https://mlsanity.com/paper/1704.08756/) (2017)
- [Neural Machine Translation with Pivot Languages](https://mlsanity.com/paper/1611.04928/) (2016)
- [On the Calibration and Uncertainty of Neural Learning to Rank Models](https://mlsanity.com/paper/2101.04356/) (2021)
- [Sounding Board: A User-Centric and Content-Driven Social Chatbot](https://mlsanity.com/paper/1804.10202/) (2018)
- [ESR: Ethics and Society Review of Artificial Intelligence Research](https://mlsanity.com/paper/2106.11521/) (2021)
- [Audrey: A Personalized Open-Domain Conversational Bot](https://mlsanity.com/paper/2011.05910/) (2020)

## Built on by (most cited first, 3 of 3)

- [POTATO: The Portable Text Annotation Tool](https://mlsanity.com/paper/2212.08620/) (2022)
- [Selecting Stickers in Open-Domain Dialogue through Multitask Learning](https://mlsanity.com/paper/2209.07697/) (2022)
- [Memes-as-Replies: Can Models Select Humorous Manga Panel Responses?](https://mlsanity.com/paper/2602.15842/) (2026)

## Abstract (arXiv)

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.