diff --git a/_publications/2015-10-01-paper-title-number-3.md b/_publications/2015-10-01-paper-title-number-3.md deleted file mode 100644 index d019281dcba22..0000000000000 --- a/_publications/2015-10-01-paper-title-number-3.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -title: "Paper Title Number 3" -collection: publications -permalink: /publication/2015-10-01-paper-title-number-3 -excerpt: 'This paper is about the number 3. The number 4 is left for future work.' -date: 2015-10-01 -venue: 'Journal 1' -paperurl: 'http://academicpages.github.io/files/paper3.pdf' -citation: 'Your Name, You. (2015). "Paper Title Number 3." Journal 1. 1(3).' -published: false ---- -This paper is about the number 3. The number 4 is left for future work. - -[Download paper here](http://academicpages.github.io/files/paper3.pdf) - -Recommended citation: Your Name, You. (2015). "Paper Title Number 3." Journal 1. 1(3). \ No newline at end of file diff --git a/_publications/2010-10-01-paper-title-number-2.md b/_publications/2024-02-20-paper-title-number-2.md similarity index 100% rename from _publications/2010-10-01-paper-title-number-2.md rename to _publications/2024-02-20-paper-title-number-2.md diff --git a/_publications/2024-03-15-paper-title-number-3.md b/_publications/2024-03-15-paper-title-number-3.md new file mode 100644 index 0000000000000..087b2c13acbb1 --- /dev/null +++ b/_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. \ No newline at end of file