A case atudy of closed-domain response suggestion with limited training data
- 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.
Verfasserangaben: | Lukas GalkeORCiD, Gunnar Gerstenkorn, Ansgar ScherpORCiDGND |
---|---|
DOI: | https://doi.org/10.1007/978-3-319-99133-7_18 |
ISBN: | 978-3-319-99133-7 |
ISBN: | 978-3-319-99132-0 |
ISSN: | 1865-0929 |
ISSN: | 1865-0937 |
Titel des übergeordneten Werks (Englisch): | Database and Expert Systems Applications : DEXA 2018 Iinternational workshops |
Verlag: | Springer |
Verlagsort: | Berlin |
Publikationstyp: | Sonstiges |
Sprache: | Englisch |
Datum der Erstveröffentlichung: | 07.08.2018 |
Erscheinungsjahr: | 2018 |
Datum der Freischaltung: | 24.02.2022 |
Band: | 903 |
Seitenanzahl: | 12 |
Erste Seite: | 218 |
Letzte Seite: | 229 |
Fördernde Institution: | EU H2020 project MOVING [693092] |
Organisationseinheiten: | Digital Engineering Fakultät / Hasso-Plattner-Institut für Digital Engineering GmbH |
DDC-Klassifikation: | 0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 000 Informatik, Informationswissenschaft, allgemeine Werke |
Peer Review: | Referiert |
Publikationsweg: | Open Access / Green Open-Access |