Generative Multimodal Entity Linking

06/22/2023
by   Senbao Shi, et al.
0

Multimodal Entity Linking (MEL) is the task of mapping mentions with multimodal contexts to the referent entities from a knowledge base (e.g., Wikipedia). Prior MEL methods mainly focus on designing complex multimodal interaction mechanisms and require fine-tuning all model parameters, which can be prohibitively costly and difficult to scale in the era of Large Language Models (LLMs). In this work, we propose GEMEL, a simple yet effective Generative Multimodal Entity Linking method, which leverages the capabilities of LLMs from large-scale pre-training to directly generate target entity names. We keep the vision and language model frozen and only train a linear layer to enable cross-modality interactions. To adapt LLMs to the MEL task, we take advantage of the emerging in-context learning (ICL) capability of LLMs by retrieving multimodal instances as demonstrations. Extensive experiments show that with only  0.3 state-of-the-art results on two well-established MEL datasets (4.1 gains on WikiDiverse and 15.4 compatible with any off-the-shelf language model, paving the way towards an efficient and general solution for utilizing LLMs in the MEL task.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset