SyncAI.news, a Varaisys broadcasting
Seeing Isn't Resolving: Visual and Linguistic Disambiguation with Conversational Grounding
EC

Edoardo Cecchinato, Shun Inadumi, Angel Garc\'ia Contreras, Giuseppe Riccardi, Koichiro Yoshino

· 1 min read

ResearcharXiv cs.CL

Seeing Isn't Resolving: Visual and Linguistic Disambiguation with Conversational Grounding

arXiv:2611.21183v1 Announce Type: new Abstract: Visual grounding benchmarks usually do not consider the contextual uncertainty of real-world scenarios. In this study, we construct a novel benchmark, the Japanese evaluation for Ambiguous visual Grounding with Dialogue (JAG-D) dataset. It consists of human-robot conversational multimodal interactions covering different types of ambiguity, arising from visual and linguistic categories. We evaluate the capabilities of different state-of-the-art Visual Language Models (VLMs) for ambiguity recognition and resolution. We compare dialogue context grounding performance for visual and linguistic ambiguity resolution. Our experiments show that VLMs can substantially improve the resolution of linguistic ambiguity, especially Japanese zero anaphora, by using dialogue context. We further conduct a comparative analysis to understand whether grounding improvements arise from the semantic content of the dialogue or from its conversational structure.

Original source

This story was published by arXiv cs.CL and written by Edoardo Cecchinato, Shun Inadumi, Angel Garc\'ia Contreras, Giuseppe Riccardi, Koichiro Yoshino. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News