A Knowledge-Grounded Multimodal Search-Based Conversational Agent
This work addresses the problem of enhancing conversational agents with multimodal and knowledge-grounded capabilities for users in interactive search scenarios, representing an incremental advancement.
The paper tackled the challenge of multimodal search-based dialogue by developing a neural response generation system that incorporates knowledge base information, achieving a substantial improvement of over 9 BLEU points in text-based similarity measures.
Multimodal search-based dialogue is a challenging new task: It extends visually grounded question answering systems into multi-turn conversations with access to an external database. We address this new challenge by learning a neural response generation system from the recently released Multimodal Dialogue (MMD) dataset (Saha et al., 2017). We introduce a knowledge-grounded multimodal conversational model where an encoded knowledge base (KB) representation is appended to the decoder input. Our model substantially outperforms strong baselines in terms of text-based similarity measures (over 9 BLEU points, 3 of which are solely due to the use of additional information from the KB.