Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model that leverages the document structure to provide dialogue-contextualized passage encodings and better locate knowledge relevant to the conversation. An auxiliary loss captures the history of dialogue-document connections. We demonstrate the effectiveness of our model on two document-grounded conversational datasets and provide analyses showing generalization to unseen documents and long dialogue contexts.
@article{arxiv.2109.04673,
title = {DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization},
author = {Zeqiu Wu and Bo-Ru Lu and Hannaneh Hajishirzi and Mari Ostendorf},
journal= {arXiv preprint arXiv:2109.04673},
year = {2021}
}