DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization
arXiv:2109.04673
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.
arXiv commentEMNLP 2021 camera-ready
References in corpus (5)
- Longformer: The Long-Document Transformer
- Tracking the World State with Recurrent Entity Networks
- Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
- Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering
- Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering