%0 Conference Proceedings %T DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization %A Wu, Zeqiu %A Lu, Bo-Ru %A Hajishirzi, Hannaneh %A Ostendorf, Mari %Y Moens, Marie-Francine %Y Huang, Xuanjing %Y Specia, Lucia %Y Yih, Scott Wen-tau %S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing %D 2021 %8 November %I Association for Computational Linguistics %C Online and Punta Cana, Dominican Republic %F wu-etal-2021-dialki %X 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. %R 10.18653/v1/2021.emnlp-main.140 %U https://aclanthology.org/2021.emnlp-main.140 %U https://doi.org/10.18653/v1/2021.emnlp-main.140 %P 1852-1863