Large Language Models and Multimodal Retrieval for Visual Word Sense Disambiguation

Abstract

Visual Word Sense Disambiguation (VWSD) is a novel challenging task with the goal of retrieving an image among a set of candidates, which better represents the meaning of an ambiguous word within a given context. In this paper, we make a substantial step towards unveiling this interesting task by applying a varying set of approaches. Since VWSD is primarily a text-image retrieval task, we explore the latest transformer-based methods for multimodal retrieval. Additionally, we utilize Large Language Models (LLMs) as knowledge bases to enhance the given phrases and resolve ambiguity related to the target word. We also study VWSD as a unimodal problem by converting to text-to-text and image-to-image retrieval, as well as question-answering (QA), to fully explore the capabilities of relevant models. To tap into the implicit knowledge of LLMs, we experiment with Chain-of-Thought (CoT) prompting to guide explainable answer generation. On top of all, we train a learn to rank (LTR) model in order to combine our different modules, achieving competitive ranking results. Extensive experiments on VWSD demonstrate valuable insights to effectively drive future directions.

Conference on Empirical Methods in Natural Language Processing (EMNLP) 2023

References in corpus (10)

• Large Language Models are Zero-Shot Reasoners
• BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
• Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
• A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
• Galactica: A Large Language Model for Science
• A Review on Language Models as Knowledge Bases
• Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
• Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning
• The Contribution of Knowledge in Visiolinguistic Learning: A Survey on Tasks and Challenges
• Language Models as Knowledge Bases for Visual Word Sense Disambiguation