2021/05/13 by Silin Gao, Gao, Silin, Ryuichi Takanobu +7 · 1 citation
Computer Science · Engineering · #Artificial intelligence #Big data #Computation and Language (cs.CL) #Computer science #Data mining #Data science #Dialog box #End-to-end principle #Engineering #FOS: Computer and information sciences #Grounded theory #Knowledge extraction #Knowledge management #Natural Language Processing Techniques #Natural language processing #Pipeline (software) #Programming language #Qualitative research #Speech and dialogue systems #Systems engineering #Task (project management) #Topic Modeling #Unstructured data #World Wide Web #cs.CL
paper · pdf · doi:10.48550/arxiv.2105.06041
published in arXiv (Cornell University) (Cornell University) · Findings of ACL-IJCNLP 2021, long paper
openalex publication_date 2021/05/13 · arxiv created 2021/06/02 · arxiv updated 2021/06/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Task-oriented dialog (TOD) systems typically manage structured knowledge (e.g. ontologies and databases) to guide the goal-oriented conversations. However, they fall short of handling dialog turns grounded on unstructured knowledge (e.g. reviews and documents). In this paper, we formulate a task of modeling TOD grounded on both structured and unstructured knowledge. To address this task, we propose a TOD system with hybrid knowledge management, HyKnow. It extends the belief state to manage both structured and unstructured knowledge, and is the first end-to-end model that jointly optimizes dialog modeling grounded on these two kinds of knowledge. We conduct experiments on the modified version of MultiWOZ 2.1 dataset, where dialogs are grounded on hybrid knowledge. Experimental results show that HyKnow has strong end-to-end performance compared to existing TOD systems. It also outperforms the pipeline knowledge management schemes, with higher unstructured knowledge retrieval accuracy.