Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures

Multimodal reference resolution, including phrase grounding, aims to understand the semantic relations between mentions and realworld objects. Phrase grounding between images and their captions is a well-established task. In contrast, for real-world applications, it is essential to integrate textual and multimodal reference resolution to unravel the reference relations within dialogue, especially in handling ambiguities caused by pronouns and ellipses. This paper presents a framework that unifies textual and multimodal reference resolution by mapping mention embeddings to object embeddings and selecting mentions or objects based on their similarity. 1 Our experiments show that learning textual reference resolution, such as coreference resolution and predicateargument structure analysis, positively affects performance in multimodal reference resolution. In particular, our model with coreference resolution performs better in pronoun phrase grounding than representative models for this task, MDETR and GLIP. Our qualitative analysis demonstrates that incorporating textual reference relations strengthens the confidence scores between mentions, including pronouns and predicates, and objects, which can reduce the ambiguities that arise in visually grounded dialogues. * Currently at NEC Corporation. 1 The code is publicly available at https://github.com/ SInadumi/mmrr . Would you [Φ NOM ] この コップ を [Φ DAT ] 取っ て 頂けますか ? me DAT this cup ACC take you NOM FPV of the System … Dialogue Text P 2 : Person 2 P 1 : Person 1 はい。 コーヒー カップ ですよね。 Yes. the coffee cup correct ? Indirect (DAT) Direct (Coref.