Large Language Models and Multimodal Retrieval for Visual Word Sense Disambiguation

Published: 07 Oct 2023, Last Modified: 01 Dec 2023EMNLP 2023 MainEveryoneRevisionsBibTeX
Submission Type: Regular Long Paper
Submission Track: Speech and Multimodality
Submission Track 2: NLP Applications
Keywords: visual word sense disambiguation, large language models, multimodal retrieval
TL;DR: One of the first attempts to explore the task of visual word sense disambiguation using a variety of techniques.
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.
Submission Number: 2849
Loading