Introducing Multi-modality in Persuasive Task Oriented Virtual Sales Agent

Raut, Aritra; Das, Subrata; Tiwari, Abhisek; Saha, Sriparna; Maitra, Anutosh; Ramnani, Roshni; Sengupta, Shamik

doi:10.1007/978-3-031-30111-7_46

Cited by 2 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The paper (Qiu and Zhang, 2021) presents a personalized end-toend task-oriented conversation system that uses a memory network to provide appealing and personaconsistent responses. In recent articles, the researchers (Tiwari et al, 2021(Tiwari et al, , 2022 highlighted the DST(Dialogue State Tracker) module's application in task-oriented conversation agents to carry out persuasion in order to effectively identify and respond to changing user demands. Other than this, a meta-learned end-to-end model using GPT-2 has been proposed (Raut et al, 2022(Raut et al, , 2023 to produce persuasive dialogues in task oriented dialogue generation setting.…”

Section: Related Workmentioning

confidence: 99%

Sentiment Aided Graph Attentive Contextualization for Task Oriented Negotiation Dialogue Generation

Raut,

Saha,

Maitra

et al. 2023

Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacifi

View full text Add to dashboard Cite

Over the past several years, the demand and popularity of using virtual assistants to finish jobs like service scheduling and online shopping have increased. While keeping the user's request in mind, an effective task-oriented virtual agent must strive to improve the seller's profit. Therefore, in order to achieve the best possible trade-off between the parties, this form of virtual agent has to have strong negotiating abilities. Although current conversational agents are quite good at making fluent sentences, they are still unable to use strategic thinking. In order to more effectively contextualize the choice of the next set of negotiation methods while producing answers, we develop Nego-GAT, an end-to-end negotiation system that includes sentiment information and graph attention embedding into GPT-2. Our selfsupervised model outperforms earlier cuttingedge negotiation models in terms of both the precision of strategy/dialogue act prediction and the caliber of the generated dialogue responses 1 .

show abstract