2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) 2018
DOI: 10.1109/icmla.2018.00079
|View full text |Cite
|
Sign up to set email alerts
|

A Persona-Based Multi-turn Conversation Model in an Adversarial Learning Framework

Abstract: In this paper, we extend the persona-based sequenceto-sequence (Seq2Seq) neural network conversation model to multi-turn dialogue by modifying the state-of-the-art hredGAN architecture. To achieve this, we introduce an additional input modality into the encoder and decoder of hredGAN to capture other attributes such as speaker identity, location, sub-topics, and other external attributes that might be available from the corpus of human-to-human interactions. The resulting persona hredGAN (phredGAN ) shows bett… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
3
3

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(5 citation statements)
references
References 11 publications
0
5
0
Order By: Relevance
“…Personalized conversation models capture speaker's characteristic, such as language behaviors, styles, and hobbies. (Li et al 2016b;Zhang et al 2018b;Olabiyi, Khazane, and Mueller 2018;Song et al 2020;Zheng et al 2020). Some researchers focused on the conversational agent being aware of the human's personality and adjusting the dialogue accordingly (Lucas et al 2009;Joshi, Mi, and Faltings 2017;Luo et al 2019).…”
Section: Personalized Conversation Modelsmentioning
confidence: 99%
See 1 more Smart Citation
“…Personalized conversation models capture speaker's characteristic, such as language behaviors, styles, and hobbies. (Li et al 2016b;Zhang et al 2018b;Olabiyi, Khazane, and Mueller 2018;Song et al 2020;Zheng et al 2020). Some researchers focused on the conversational agent being aware of the human's personality and adjusting the dialogue accordingly (Lucas et al 2009;Joshi, Mi, and Faltings 2017;Luo et al 2019).…”
Section: Personalized Conversation Modelsmentioning
confidence: 99%
“…Appropriateness. We evaluate the overall quality by measuring the matching between the ground-truth and generated responses on three metrics: BLEU (Papineni et al 2002), NIST (Doddington 2002), and CIDEr (Vedantam, Lawrence Zitnick, and Parikh 2015). 2.…”
Section: Evaluation Metricsmentioning
confidence: 99%
“…We use DialogWAE-GMP which outperforms DialogWAE by using the Gaussian mixture prior. Metrics To quantitatively compare the response generation performance of VHUCM-PUE with other models, we use various automatic metrics used in (Park et al, 2018;Du et al, 2018;Olabiyi et al, 2018;Gu et al, 2019).…”
Section: Experiments Setupmentioning
confidence: 99%
“…They incorporate the speakers to generate the responses, but Li et al (2016b) only considers a short context of the conversation. Olabiyi et al (2018) overcomes this, but the user information is still in the utterance level. This approach tends to generate the same response for the same speaker even when the given utterances are different.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation