Domain-Specific Lexical Grounding in Noisy Visual-Textual Documents

TL;DR

This paper introduces an unsupervised clustering approach to lexical grounding in noisy, domain-specific image-text documents, effectively capturing local contextual meanings without detailed annotations.

Contribution

It presents a novel unsupervised method for lexical grounding in multi-image, multi-sentence documents, addressing the challenge of domain-specific contextual understanding.

Findings

Improved precision and recall over object detection baselines

Effective in capturing local contextual meanings of words

Demonstrated on real estate and Wikipedia datasets

Abstract

Images can give us insights into the contextual meanings of words, but current image-text grounding approaches require detailed annotations. Such granular annotation is rare, expensive, and unavailable in most domain-specific contexts. In contrast, unlabeled multi-image, multi-sentence documents are abundant. Can lexical grounding be learned from such documents, even though they have significant lexical and visual overlap? Working with a case study dataset of real estate listings, we demonstrate the challenge of distinguishing highly correlated grounded terms, such as "kitchen" and "bedroom", and introduce metrics to assess this document similarity. We present a simple unsupervised clustering-based method that increases precision and recall beyond object detection and image tagging baselines when evaluated on labeled subsets of the dataset. The proposed method is particularly effective for local contextual meanings of a word, for example associating "granite" with countertops in the real estate dataset and with rocky landscapes in a Wikipedia dataset.