Published September 6, 2018 | Version v1
Conference paper Open

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

  • 1. Kiel University
  • 2. University of Potsdam
  • 3. University of Stirling


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 retrieval-based, conditioned-generation, and dedicated representation learning approaches for response suggestion. Our results show that retrieval-based methods that strive to find similar, known contexts are preferable over parametric approaches from the conditioned-generation family, when the training data is limited. We, however, identify a specific representation learning approach that is competitive to the retrieval-based approaches despite the training data limitation.


This is a post-peer-review, pre-copyedit version of a paper published in Elloumi M, Granitzer M, Hameurlain A, Seifert C, Stein B, Tjoa A & Wagner R (eds.) Database and Expert Systems Applications. DEXA 2018. Communications in Computer and Information Science, 903. The final authenticated version is available online at:



Additional details


MOVING – Training towards a society of data-savvy information professionals to enable open leadership innovation 693092
European Commission