A Case Study of Closed-Domain Response Suggestion with Limited Training Data

Conference object English OPEN
Galke, Lukas; Gerstenkorn, Gunnar; Scherp, Ansgar;

We analyze the problem of response suggestion in a closed domain along a real-world scenario of a digital library. We present a text-processing pipeline to generate question-answer pairs from chat transcripts. On this limited amount of training data, we compare retrieva... View more
Share - Bookmark

  • Download from
    ZENODO via ZENODO (Conference object, 2018)
  • Funded by
  • Cite this publication