Improving Dialogue Smoothing with A-priori State Pruning
Autores: Manex Serras Saenz María Inés Torres
Fecha: 17.04.2020
Abstract
When Dialogue Systems (DS) face real usage, a challenge to solve is managing unforeseen situations without breaking the coherence of the dialogue. One way to achieve this is by redirecting the interaction to known dialogue states in a transparent way. This work proposes a simple a-priori pruning method to rule out invalid candidates when searching for similar dialogue states in unexpected scenarios. The proposed method is evaluated on a User Model (UM) based on Attributed Probabilistic Finite State Bi-Automata (A-PFSBA), trained on the Dialogue State Tracking Challenge 2 (DSTC2) corpus. Results show that the proposed technique improves response times and achieves higher F1 scores than previous A-PFSBA implementations and deep learning models.
BIB_text
title = {Improving Dialogue Smoothing with A-priori State Pruning},
pages = {607-614},
keywds = {
Dialogue State Pruning, Dialogue Breakdown, Attributed Probabilistic Finite State Bi-Automata, Dialogue Systems
}
abstract = {
When Dialogue Systems (DS) face real usage, a challenge to solve is managing unforeseen situations without breaking the coherence of the dialogue. One way to achieve this is by redirecting the interaction to known dialogue states in a transparent way. This work proposes a simple a-priori pruning method to rule out invalid candidates when searching for similar dialogue states in unexpected scenarios. The proposed method is evaluated on a User Model (UM) based on Attributed Probabilistic Finite State Bi-Automata (A-PFSBA), trained on the Dialogue State Tracking Challenge 2 (DSTC2) corpus. Results show that the proposed technique improves response times and achieves higher F1 scores than previous A-PFSBA implementations and deep learning models.
}
isbn = {978-989-758-397-1},
date = {2020-04-17},
}
