cTBL: Augmenting Large Language Models for Conversational Tables

03/21/2023
by   Anirudh S Sundar, et al.
0

An open challenge in multimodal conversational AI requires augmenting large language models with information from textual and non-textual sources for multi-turn dialogue. To address this problem, this paper introduces Conversational Tables (cTBL), a three-step encoder-decoder approach to retrieve tabular information and generate dialogue responses grounded on the retrieved information. cTBL uses Transformer encoder embeddings for Dense Table Retrieval and obtains up to 5 sparse retrieval on the HyrbiDialogue dataset. Additionally, cTBL performs tabular knowledge retrieval using both encoder and decoder models, resulting in up to 46 response generation on HyrbiDialogue.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset