| Challenge: | Incorporating multi-modal contexts in conversation is important for developing engaging dialogue systems. |
| Approach: | They propose a large scale Chinese multi-modal dialogue corpus that contains image-grounded dialogues from real conversations on social media. |
| Outcome: | The proposed model can handle sparsity issues in dialogue generation tasks by incorporating image features. |
Similar Papers
MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation (2023.acl-long)
Copied to clipboard
| Challenge: | MMDialog is a dataset of 1.08 million real-world dialogues with 1.53 million unique images across 4,184 topics. |
| Approach: | They propose to use a curated set of 1.08 million dialogues with 1.53 million unique images to generalize the open domain. |
| Outcome: | The proposed system can predict responses to multi-modal content with state-of-the-art techniques and measure their performance. |
Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies focus on image-sharing behavior in singular sessions, leading to limited long-term social interaction. |
| Approach: | They propose a large-scale long-term multi-modal dialogue dataset that generates long-time multi-modity dialogue distilled from ChatGPT and proposed image aligner. |
| Outcome: | The proposed framework generates long-term multi-modal dialogue from ChatGPT and image aligner. |
Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images (2021.acl-short)
Copied to clipboard
| Challenge: | Existing training methods for multi-modal dialogue systems rely on image captioning or visual question answering datasets that are irrelevant to the dialogue context. |
| Approach: | They propose to create a 45k multi-modal dialogue dataset with minimal human intervention . they use text dialogue datasets, image-mixed dialogues and contextual-similarity filtering . |
| Outcome: | The proposed dataset can be used as training data for multi-modal dialogue systems . human evaluations show that the model can be effectively used . |
MPCHAT: Towards Multimodal Persona-Grounded Conversation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing research on persona-based dialogue has focused on textual persona that delivers personal facts or personalities, but image modality can reveal the speaker’s personal characteristics and experiences in episodic memory. |
| Approach: | They propose a multimodal persona-based dialogue dataset which extends persona with both text and images to contain episodic memories. |
| Outcome: | The proposed dataset extends persona with text and images to contain episodic memories. |
MultiDM-GCN: Aspect-guided Response Generation in Multi-domain Multi-modal Dialogue System using Graph Convolutional Network (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research suggests that engaging conversations include visual cues (e.g., a video or images) or audio cue. |
| Approach: | They propose a multi-modal conversational framework that generates the responses following the different aspects of a product or service to cater to the user's needs. |
| Outcome: | The proposed framework outperforms baselines for the task-oriented dialogue setup. |
LiveChat: A Large-Scale Personalized Dialogue Dataset Automatically Constructed from Live Streaming (2023.acl-long)
Copied to clipboard
| Challenge: | a recent study shows that open-domain dialogue systems are not able to perform well in fast-growing scenarios such as live streaming due to the domain gap between online-post constructed data and those required in downstream conversational tasks. |
| Approach: | They propose to train a conversational agent based on large social media datasets with multiple domains to improve response in live streaming scenarios. |
| Outcome: | The proposed model improves response modeling and addressee recognition in live open-domain scenarios. |
MMCoQA: Conversational Question Answering over Text, Tables, and Images (2022.acl-long)
Copied to clipboard
| Challenge: | Existing conversational QA systems only use a single knowledge source, e.g., paragraphs or knowledge graph, and assume it contains enough evidence to extract answers to users' questions. |
| Approach: | They propose a task to answer users' questions with multimodal knowledge sources via multi-turn conversations using a multimodal dataset. |
| Outcome: | The proposed task brings a series of research challenges, including but not limited to priority, consistency, and complementarity of multimodal knowledge. |
MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets (2024.naacl-long)
Copied to clipboard
Hossein Aboutalebi, Hwanjun Song, Yusheng Xie, Arshit Gupta, Lijia Sun, Hang Su, Igor Shalyminov, Nikolaos Pappas, Siffi Singh, Saab Mansour
| Challenge: | Existing approaches to augment textual dialogues with retrieved images pose privacy, diversity, and quality constraints. |
| Approach: | They propose a framework to augment text-only dialogues with diverse and high-quality images by using a diffusion model and a feedback loop. |
| Outcome: | The proposed framework is comparable to or better than baselines, with significant improvements in human evaluation, especially against retrieval baselines where the image database is small. |
M3ED: Multi-modal Multi-scene Multi-label Emotional Dialogue Database (2022.acl-long)
Copied to clipboard
| Challenge: | Existing data resources to support multimodal affective analysis in dialogues are limited in scale and diversity. |
| Approach: | They propose a multimodal multi-scene multi-label Emotional Dialogue dataset, M3ED, which contains 990 dyadic emotional dialogues from 56 different TV series. |
| Outcome: | The proposed dataset contains 990 dyadic emotional dialogues from 56 different TV series, a total of 9,082 turns and 24,449 utterances. |
Game-Based Video-Context Dialogue (D18-1)
Copied to clipboard
| Challenge: | Current dialogue systems focus more on textual and speech context knowledge and are usually based on two speakers. |
| Approach: | They propose to use live soccer game videos and Twitch.tv chats to develop visual-grounded dialogue models. |
| Outcome: | The proposed model can generate relevant temporal and spatial event language from live video and chat history while also being relevant to chat history. |