2021
DOI: 10.1007/s10489-021-02660-4
|View full text |Cite
|
Sign up to set email alerts
|

Diverse dialogue generation by fusing mutual persona-aware and self-transferrer

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
9
1

Relationship

0
10

Authors

Journals

citations
Cited by 17 publications
(5 citation statements)
references
References 27 publications
0
5
0
Order By: Relevance
“…However, the inherent limitation of input text in providing sufficient knowledge poses challenges for neural generation models to achieve the desired output quality [25][26][27]. Many research efforts have been made to enhance the control of generation with various desired properties, such as topic [28], emotion [29], keywords [30], dialogue intent [31], etc. In particular, narrative generation requires models to produce fluent and logically coherent stories based on predefined conditions [32][33][34].…”
Section: Knowledge-enhanced Text Generationmentioning
confidence: 99%
“…However, the inherent limitation of input text in providing sufficient knowledge poses challenges for neural generation models to achieve the desired output quality [25][26][27]. Many research efforts have been made to enhance the control of generation with various desired properties, such as topic [28], emotion [29], keywords [30], dialogue intent [31], etc. In particular, narrative generation requires models to produce fluent and logically coherent stories based on predefined conditions [32][33][34].…”
Section: Knowledge-enhanced Text Generationmentioning
confidence: 99%
“…Recently, many studies have explored different approaches to personalized dialogue generation (Yang et al 2020;Song et al 2020;Zheng et al 2020;Wu et al 2020;Xu et al 2021). P 2 BOT (Liu et al 2020) and TTransfo (Wolf et al 2019b) The aforementioned approaches require additional personal data (i.e., profiles) for inference.…”
Section: Personalized Dialoguementioning
confidence: 99%
“…We perform our experiments on the PersonaChat ConvAI2 dataset [22], which has been used in the past for conversation models [41][42][43]. We generate training and testing data by taking the current utterances and their corresponding context (ignoring the persona information available from ConvAI2).…”
Section: Dataset 41 the Personachat Convai2 Datasetmentioning
confidence: 99%