Augmenting dialogue generation using dialogue act embeddings: a transfer learning approach

dc.accession.numberT00879
dc.accession.number006.35 BIS
dc.contributor.advisorMajumder, Prasenjit
dc.contributor.authorBisht, Abhimanyu Singh
dc.date.accessioned2020-09-22T05:21:26Z
dc.date.accessioned2025-06-28T10:28:40Z
dc.date.available2023-02-17T05:21:26Z
dc.date.issued2020
dc.degreeM. Tech
dc.description.abstractThe following work looks at contemporary end-to-end dialogue systems with the aim of improving dialogue generation in an open-domain setting. It provides an overview of popular literature in the domain of dialogue generation, followed by a brief look at how human dialogue is understood from the perspective of Linguistics and Cognitive Science. We try to extract useful ideas from these domains of research and implement them in a transfer learning approach where a pretrained language model is supplemented with dialogue act information using special embeddings. The hypothesis behind the proposed approach is that the dialogue act information will aid the generation process. The proposed approach is then compared with a baseline approach on their performance on the DailyDialog[12] dataset using perplexity as the evaluation metric. Though the proposed approach is a significant improvement over the baseline, the contribution of the Dialogue Act Embeddings in the development is shown to be marginal via ablation analysis.
dc.identifier.citationBisht, Abhimanyu Singh (2020). Augmenting dialogue generation using dialogue act embeddings: a transfer learning approach. Dhirubhai Ambani Institute of Information and Communication Technology. vii, 50 p. (Acc.No: T00879)
dc.identifier.urihttp://drsr.daiict.ac.in/handle/123456789/957
dc.publisherDhirubhai Ambani Institute of Information and Communication Technology
dc.student.id201811051
dc.subjectNatural language processing
dc.subjectDeep learning
dc.subjectDialogue generation
dc.subjectTransfer learning
dc.subjectDialogue acts
dc.titleAugmenting dialogue generation using dialogue act embeddings: a transfer learning approach
dc.typeDissertation

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
201811051.pdf
Size:
1 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Plain Text
Description: