Probabilistic Labeling for Efficient Referential Grounding based on Collaborative Discourse
Changsong Liu, Lanbo She, Rui Fang, Joyce Yue Chai · 2014
When humans and artificial agents (e.g.robots) have mismatched perceptions of the shared environment, referential communication between them becomes difficult.To mediate perceptual differences, this paper presents a new approach using probabilistic labeling for referential grounding.This approach aims to integrate different types of evidence from the collaborative referential discourse into a unified scheme.Its probabilistic labeling procedure can generate multiple grounding hypotheses to facilitate follow-up dialogue.Our empirical results have shown the probabilistic labeling approach significantly outperforms a previous graphmatching approach for referential grounding.