Refer, Reuse, Reduce: Generating Subsequent References in Visual and Conversational Contexts
This addresses the problem of generating cohesive and effective references in dialogue for AI systems, but it is incremental as it builds on existing work in visual and conversational grounding.
The paper tackled generating first and subsequent references in visually grounded dialogue, proposing a model that produces referring utterances grounded in visual and conversational contexts, with experiments showing it generates better and more human-like references than a context-unaware model.
Dialogue participants often refer to entities or situations repeatedly within a conversation, which contributes to its cohesiveness. Subsequent references exploit the common ground accumulated by the interlocutors and hence have several interesting properties, namely, they tend to be shorter and reuse expressions that were effective in previous mentions. In this paper, we tackle the generation of first and subsequent references in visually grounded dialogue. We propose a generation model that produces referring utterances grounded in both the visual and the conversational context. To assess the referring effectiveness of its output, we also implement a reference resolution system. Our experiments and analyses show that the model produces better, more effective referring utterances than a model not grounded in the dialogue context, and generates subsequent references that exhibit linguistic patterns akin to humans.