Keywords: video-grounded dialogues, reasoning paths, semantic graphs
Abstract: Compared to traditional visual question answering, video-grounded dialogues require additional reasoning over dialogue context to answer questions in a multi-turn setting. Previous approaches to video-grounded dialogues mostly use dialogue context as a simple text input without modelling the inherent information flows at the turn level. In this paper, we propose a novel framework of Reasoning Paths in Dialogue Context (PDC). PDC model discovers information flows among dialogue turns through a semantic graph constructed based on lexical components in each question and answer. PDC model then learns to predict reasoning paths over this semantic graph. Our path prediction model predicts a path from the current turn through past dialogue turns that contain additional visual cues to answer the current question. Our reasoning model sequentially processes both visual and textual information through this reasoning path and the propagated features are used to generate the answer. Our experimental results demonstrate the effectiveness of our method and provide additional insights on how models use semantic dependencies in a dialogue context to retrieve visual cues.
One-sentence Summary: We introduce PDC, a novel approach to learn reasoning paths over semantic graphs which are built upon dialogue context at each turn, for video-grounded dialogues.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Data: [HotpotQA](https://paperswithcode.com/dataset/hotpotqa), [Visual Question Answering](https://paperswithcode.com/dataset/visual-question-answering)