Conference paper Open Access
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 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.
Name | Size | |
---|---|---|
A_Case_Study_of_Closed_Domain_Response_Suggestion_with_Limited_Training_Data.pdf
md5:571bc5ceec1bb2e130ebd00a6a56c293 |
235.3 kB | Download |
Views | 66 |
Downloads | 47 |
Data volume | 11.1 MB |
Unique views | 62 |
Unique downloads | 44 |