A multi-task BERT model for schema-guided dialogue state tracking

Καπελώνης, Ελευθέριος; Kapelonis, Eleftherios

dc.contributor.author	Καπελώνης, Ελευθέριος	el
dc.contributor.author	Kapelonis, Eleftherios	en
dc.date.accessioned	2022-10-10T06:56:02Z
dc.date.available	2022-10-10T06:56:02Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/55870
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.23568
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση 3.0 Ελλάδα	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc/3.0/gr/	*
dc.subject	Μηχανική μάθηση	el
dc.subject	Βαθιά μάθηση	el
dc.subject	Επεξεργασία φυσικής γλώσσας	el
dc.subject	Bert	en
dc.subject	Διαλογικά συστήματα	el
dc.subject	Dialogue state tracking	en
dc.subject	Μάθηση πολλαπλών εργασιών	el
dc.subject	Machine learning	en
dc.subject	Deep learning	en
dc.subject	Natural language processing	en
dc.subject	Dialogue systems	en
dc.subject	Dialogue state tracking	en
dc.subject	Multi-task learning	en
dc.title	A multi-task BERT model for schema-guided dialogue state tracking	en
heal.type	bachelorThesis
heal.classification	Machine learning	en
heal.language	el
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2022-06-14
heal.abstract	Dialogue systems often employ a Dialogue State Tracking (DST) component to successfully complete conversations. DST aims to track the user goal over the course of a dialogue and it is a particularly challenging task in multi-domain scenarios. Schema-guided DST is a new approach, where the schema, i.e. a list of the supported slots and intents along with natural language descriptions, is provided for each dialogue service. Recent state-of-the-art DST implementations rely on schemata of diverse services to improve model robustness and handle zero-shot generalization to new domains, however such methods typically require multiple large scale transformer models and long input sequences to perform well. In this diploma thesis, we first introduce the basics of machine learning, deep learning, natural language processing and dialogue systems focusing on DST. We then propose a single multi-task BERT-based model that jointly solves the three DST tasks of intent prediction, requested slot prediction and slot filling. Moreover, we propose an efficient and parsimonious encoding of the dialogue history and service schemata that is shown to further improve performance. We only encode the last two utterances, a compact schema representation and the previously predicted dialogue state. The preceding system utterance is represented as its underlying system actions which significantly benefits accuracy. For the slot filling task we additionally incorporate slot carryover mechanisms that search previous dialogue utterances and states to retrieve values when necessary. A number of classification heads which take as input various parts of the BERT-encoded sequence are jointly trained to perform the tasks. Evaluation on the SGD dataset shows that our approach outperforms the baseline SGP-DST by a large margin and performs well compared to the state-of-the-art, while being significantly more computationally efficient. Extensive ablation studies are performed to examine the contributing factors to the success of our model.	en
heal.advisorName	Ποταμιάνος, Αλέξανδρος	el
heal.committeeMemberName	Τζαφέστας, Κωνσταντίνος	el
heal.committeeMemberName	Κόλλιας, Στέφανος	el
heal.committeeMemberName	Ποταμιάνος, Αλέξανδρος	el
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών. Τομέας Σημάτων, Ελέγχου και Ρομποτικής	el
heal.academicPublisherID	ntua
heal.numberOfPages	110 σ.	el
heal.fullTextAvailability	false