Semi-supervised multimodal coreference resolution in image narrations

Arushi Goel, Basura Fernando, Frank Keller, Hakan Bilen

Submission Type: Regular Long Paper

Submission Track: Language Grounding to Vision, Robotics and Beyond

Submission Track 2: Semantics: Lexical, Sentence level, Document Level, Textual Inference, etc.

Keywords: Coreference Resolution, Vision Language Understanding, Narrative Grounding, Semi-Supervised Learning

Abstract: In this paper, we study multimodal coreference resolution, specifically where a longer descriptive text, i.e., a narration is paired with an image. This poses significant challenges due to fine-grained image-text alignment, inherent ambiguity present in narrative language, and unavailability of large annotated training sets. To tackle these challenges, we present a data efficient semi-supervised approach that utilizes image-narration pairs to resolve coreferences and narrative grounding in a multimodal context. Our approach incorporates losses for both labeled and unlabeled data within a cross-modal framework. Our evaluation shows that the proposed approach outperforms strong baselines both quantitatively and qualitatively, for the tasks of coreference resolution and narrative grounding.

Submission Number: 981