K-ESIM and T-ESIM extend ESIM by incorporating domain knowledge and similar-dialog information, yielding preliminary accuracy gains on Ubuntu and Advising datasets for next-utterance selection.
In Machine Learning and Applica- tions (ICMLA), 2017 16th IEEE International Conference on , 1120–1125
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Knowledge-incorporating ESIM models for Response Selection in Retrieval-based Dialog Systems
K-ESIM and T-ESIM extend ESIM by incorporating domain knowledge and similar-dialog information, yielding preliminary accuracy gains on Ubuntu and Advising datasets for next-utterance selection.