DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization

TL;DR

This paper presents DIALKI, a model that improves knowledge identification in conversational systems grounded in long documents by leveraging document structure and dialogue context, enhancing response relevance.

Contribution

The paper introduces a novel knowledge identification model that uses dialogue-document contextualization and auxiliary loss to improve relevance detection in long document-based conversations.

Findings

Effective in locating relevant knowledge in long documents

Generalizes well to unseen documents and long dialogues

Outperforms baseline models on two datasets

Abstract

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.