Developing Better Models for Dialogue Threads and Responses

dc.contributor.authorLi, Tiandaen
dc.contributor.departmentElectrical and Computer Engineeringen
dc.contributor.supervisorZhu, Xiaodan
dc.date.accessioned2020-09-09T21:39:09Z
dc.date.available2020-09-09T21:39:09Z
dc.degree.grantorQueen's University at Kingstonen
dc.description.abstractIn this thesis, we focus on developing machine learning algorithms to model human dialogues and conversations by investigating three basic tasks. We first study the development of retrieval-based chatbots, in which the models aim to recommend the most appropriate responses for users based on the dialogue context. We propose a pretrained-based SA-BERT method to incorporate the identities of speakers which outperforms all existing models on four benchmark datasets. In the second task, we aim to help users to better access the dialogue history by proposing novel models for dialogue disentanglement. Specifically, multiple threads of discussions in the same dialogue are disentangled and organized to single topic threads. This research can help users to more easily follow up on the topics discussed in complex dialogues. We propose a hierarchical model by considering both single utterance and context semantics, which achieves new state-of-the-art performance on two datasets. In the third task, we are concerned with the outcome of dialogues --- determining if users' questions or problems have been addressed or answered in a dialogue, and if so, where they are addressed in the dialogue. Different from the previous study in which the contribution of each utterance towards the outcome is a black-box, we perform a pilot study by adding interpretability through determining if each utterance is contributing to addressing the user's questions. Our attention-based model is shown to achieve the best-reported performance on the evaluation dataset.en
dc.description.degreeM.A.Sc.en
dc.embargo.liftdate2025-09-03T18:41:13Z
dc.embargo.termsThe third and fourth chapters are under the review of conferences (EMNLP and COLING). Due to the regulation of the conference, related work is not allowed to be published during the anonymity period. As a result, I request not to publish my thesis until my paper got accepted.en
dc.identifier.urihttp://hdl.handle.net/1974/28105
dc.language.isoengen
dc.relation.ispartofseriesCanadian thesesen
dc.rightsQueen's University's Thesis/Dissertation Non-Exclusive License for Deposit to QSpace and Library and Archives Canadaen
dc.rightsProQuest PhD and Master's Theses International Dissemination Agreementen
dc.rightsIntellectual Property Guidelines at Queen's Universityen
dc.rightsCopying and Preserving Your Thesisen
dc.rightsThis publication is made available by the authority of the copyright owner solely for the purpose of private study and research and may not be copied or reproduced except as permitted by the copyright laws without written authority from the copyright owner.en
dc.subjectDialogue Systemen
dc.subjectResponse Selectionen
dc.subjectMultiple Participantsen
dc.subjectDialogue Disentanglementen
dc.subjectDeep Contextualized Utterance Representationsen
dc.subjectNatural Language Processingen
dc.titleDeveloping Better Models for Dialogue Threads and Responsesen
dc.typethesisen
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Li_Tianda_202009_MASC.pdf
Size:
778.81 KB
Format:
Adobe Portable Document Format
Description:
Thesis document
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.6 KB
Format:
Item-specific license agreed upon to submission
Description: