Detecting out-of-domain utterances addressed to a virtual personal assistant

27 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Out-of-Domain Detection for Natural Language Understanding in Dialog Systems (2019, methodology): “Significant results have been achieved by conventional methods in low-dimensional spaces [19], [22], and some of these methods have also been applied to NLU systems [23], [24].”
Out-of-Domain Detection Method Based on Sentence Distance for Dialogue Systems (2018, methodology): “[5] solve the OOD problem by applying a method for removing noisy expressions from web search queries.”
Neural sentence embedding using only in-domain sentences for out-of-domain sentence detection in dialog systems (2017, methodology): “Previous studies [12, 19, 31] on OOD sentence detection use sentence representations based on bag-of-words models, which have limitations in representing rare or unknown words; those words are likely to appear in OOD sentences.”
Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Rates (2018, methodology): “Also, the methods are evaluated either based on IND recall and OOD recall [5] or Equal Error Rate (ERR), where thresholding is used to match FAR and FRR to be the same [4, 6].”