More publication

_publications/2024-03-15-paper-title-number-3.md

@@ -0,0 +1,41 @@
+---
+title: "On Enhancing Deep Embedded Clustering for Intent
+Mining in Goal-Oriented Dialogue Understanding"
+collection: publications
+permalink: /publication/2024-03-15-paper-title-number-3
+excerpt: ''Discovering user intents plays an indispensable role in natural lan-
+guage understanding and automated dialogue response. However, labeling intents
+for new domains from scratch is a daunting process that often requires extensive
+manual effort from domain experts. To this end, this paper proposes an unsu-
+pervised approach for discovering intents and automatically producing intention
+labels from a collection of unlabeled utterances in the context of the banking
+domain. A proposed two-stage training procedure includes deploying Deep Em-
+bedded Clustering (DEC), wherein we made significant modifications by using
+the Sophia optimizer and the Jensen-Shannon divergence measure to simultane-
+ously learn feature representations and cluster assignments. A set of intent labels
+for each cluster is then generated by using a dependency parser in the second
+stage. We empirically show that the proposed unsupervised approach is capable
+of generating meaningful intent labels and short text clustering while achieving
+high evaluation scores.''
+date: 2024-03-15
+venue: 'Journal of Uncertain Systems'
+paperurl: 'Pending'
+citation: 'Pending'
+published: True
+---
+Discovering user intents plays an indispensable role in natural lan-
+guage understanding and automated dialogue response. However, labeling intents
+for new domains from scratch is a daunting process that often requires extensive
+manual effort from domain experts. To this end, this paper proposes an unsu-
+pervised approach for discovering intents and automatically producing intention
+labels from a collection of unlabeled utterances in the context of the banking
+domain. A proposed two-stage training procedure includes deploying Deep Em-
+bedded Clustering (DEC), wherein we made significant modifications by using
+the Sophia optimizer and the Jensen-Shannon divergence measure to simultane-
+ously learn feature representations and cluster assignments. A set of intent labels
+for each cluster is then generated by using a dependency parser in the second
+stage. We empirically show that the proposed unsupervised approach is capable
+of generating meaningful intent labels and short text clustering while achieving
+high evaluation scores.
+
+The paper is under review.