Friends-MMC：一個用於多模態多方對話理解的數據集

Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding

December 23, 2024

作者: Yueqian Wang, Xiaojun Meng, Yuxuan Wang, Jianxin Liang, Qun Liu, Dongyan Zhao

cs.AI

摘要

多模多方對話（MMC）是一個鮮少被研究但重要的研究主題，因為它很適合真實世界的情境，因此潛在地具有更廣泛的應用。與傳統的多模對話相比，MMC 需要更強的以角色為中心的理解能力，因為在視覺和文本上下文中都出現了許多對話者。為了促進對這個問題的研究，我們在本文中提出了 Friends-MMC，這是一個包含 24,000 多個獨特發言與視頻上下文配對的 MMC 數據集。為了探索對話的以角色為中心的理解，我們還標註了每個發言者的發言、視頻中出現的臉部的名稱和邊界框。基於這個 Friends-MMC 數據集，我們進一步研究了兩個基本的 MMC 任務：對話發言者識別和對話回應預測，這兩者都具有多方性質，視頻或圖像作為視覺上下文。對於對話發言者識別，我們展示了現有方法（如預訓練模型）的效率問題，並提出了一種簡單而有效的基準方法，利用優化求解器來利用兩種模態的上下文以獲得更好的性能。對於對話回應預測，我們在 Friends-MMC 上微調生成式對話模型，並分析了發言者信息的好處。代碼和數據集可以在 https://github.com/yellow-binary-tree/Friends-MMC 公開獲得，因此我們呼籲更多關注在理解對話時塑造發言者信息。

English

Multi-modal multi-party conversation (MMC) is a less studied yet important topic of research due to that it well fits real-world scenarios and thus potentially has more widely-used applications. Compared with the traditional multi-modal conversations, MMC requires stronger character-centered understanding abilities as there are many interlocutors appearing in both the visual and textual context. To facilitate the study of this problem, we present Friends-MMC in this paper, an MMC dataset that contains 24,000+ unique utterances paired with video context. To explore the character-centered understanding of the dialogue, we also annotate the speaker of each utterance, the names and bounding bboxes of faces that appear in the video. Based on this Friends-MMC dataset, we further study two fundamental MMC tasks: conversation speaker identification and conversation response prediction, both of which have the multi-party nature with the video or image as visual context. For conversation speaker identification, we demonstrate the inefficiencies of existing methods such as pre-trained models, and propose a simple yet effective baseline method that leverages an optimization solver to utilize the context of two modalities to achieve better performance. For conversation response prediction, we fine-tune generative dialogue models on Friend-MMC, and analyze the benefits of speaker information. The code and dataset is publicly available at https://github.com/yellow-binary-tree/Friends-MMC and thus we call for more attention on modeling speaker information when understanding conversations.