From Data to Dialogue: Leveraging the Structure of Knowledge Graphs for Conversational Exploratory Search

This GitHub repository hosts the code and data resources accompanying the PACLIC 2023 paper titled "From Data to Dialogue: Leveraging the Structure of Knowledge Graphs for Conversational Exploratory Search."

Repository Contents:

1. agent: Contains the training data used to train the conversational agent.
2. app: Contains the conversational agent's backend and information retrieval scripts.
3. evaluation: Contains collected data from the human evaluation, including conversation logs and questionnaire results.
4. frontend: Contains scripts for the voice-based frontend used in the evaluation.
5. graph_data: Contains a Neo4j data dump of the constructed news knowledge graph.

Citation Information

For citing this study in academic papers, presentations, or theses, please use the following BibTeX entry:

@inproceedings{schneider-etal-2023-data,
    title = "From Data to Dialogue: Leveraging the Structure of Knowledge Graphs for Conversational Exploratory Search",
    author = "Schneider, Phillip  and
      Rehtanz, Nils  and
      Jokinen, Kristiina  and
      Matthes, Florian",
    editor = "Huang, Chu-Ren  and
      Harada, Yasunari  and
      Kim, Jong-Bok  and
      Chen, Si  and
      Hsu, Yu-Yin  and
      Chersoni, Emmanuele  and
      A, Pranav  and
      Zeng, Winnie Huiheng  and
      Peng, Bo  and
      Li, Yuxi  and
      Li, Junlin",
    booktitle = "Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation",
    month = dec,
    year = "2023",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.paclic-1.61",
    pages = "609--619",
}