Filtern
Volltext vorhanden
- nein (1)
Erscheinungsjahr
- 2018 (1)
Dokumenttyp
- Sonstiges (1) (entfernen)
Sprache
- Englisch (1)
Gehört zur Bibliographie
- ja (1) (entfernen)
Institut
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.