A Compare Aggregate Transformer for Understanding Document-grounded Dialogue
This work addresses document-grounded dialogue generation, an incremental improvement for enhancing response informativeness in conversational AI.
The paper tackled the problem of noise in dialogue history affecting knowledge selection for document-grounded dialogue, proposing a Compare Aggregate Transformer that outperformed state-of-the-art methods on the CMUDoG dataset.
Unstructured documents serving as external knowledge of the dialogues help to generate more informative responses. Previous research focused on knowledge selection (KS) in the document with dialogue. However, dialogue history that is not related to the current dialogue may introduce noise in the KS processing. In this paper, we propose a Compare Aggregate Transformer (CAT) to jointly denoise the dialogue context and aggregate the document information for response generation. We designed two different comparison mechanisms to reduce noise (before and during decoding). In addition, we propose two metrics for evaluating document utilization efficiency based on word overlap. Experimental results on the CMUDoG dataset show that the proposed CAT model outperforms the state-of-the-art approach and strong baselines.