|Appears in Collections:||Computing Science and Mathematics Book Chapters and Sections|
|Title:||A Case Study of Closed-Domain Response Suggestion with Limited Training Data|
|Citation:||Galke L, Gerstenkorn G & Scherp A (2018) A Case Study of Closed-Domain Response Suggestion with Limited Training Data. In: Elloumi M, Granitzer M, Hameurlain A, Seifert C, Stein B, Tjoa A & Wagner R (eds.) Communications in Computer and Information Science; Database and Expert Systems Applications. Communications in Computer and Information Science, 903. Regensburg, Germany: Springer International Publishing, pp. 218-229. https://doi.org/10.1007/978-3-319-99133-7_18|
|Series/Report no.:||Communications in Computer and Information Science, 903|
|Abstract:||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.|
|Rights:||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: https://doi.org/10.1007/978-3-319-99133-7_18|
|W42-GalkeEtAl-A Case Study of Closed-Domain Response Suggestion with Limited Training Data.pdf||Fulltext - Accepted Version||255.49 kB||Adobe PDF||View/Open|
This item is protected by original copyright
Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
If you believe that any material held in STORRE infringes copyright, please contact email@example.com providing details and we will remove the Work from public display in STORRE and investigate your claim.