Personalizing Dialogue Agents via Meta-Learning

Madotto, Andrea; Lin, Zhaojiang; Wu, Chien-Sheng; Fung, Pascale

doi:10.18653/v1/p19-1542

Cited by 133 publications

(115 citation statements)

References 31 publications

Supporting

Mentioning

113

Contrasting

Order By: Relevance

“…By applying such methods on NLG, the model can get better results in a low-resource setting and show better domain generalization [90,91]. Madotto et al [92] further extended this method for personalized dialog systems by leveraging only a few dialogue samples collected from the target user without using the persona-specific descriptions.…”

Section: Transfer Learningmentioning

confidence: 99%

Recent advances and challenges in task-oriented dialog systems

Zhang

Takanobu

Huang

et al. 2020

Sci. China Technol. Sci.

105

View full text Add to dashboard Cite

Due to the significance and value in human-computer interaction and natural language processing, task-oriented dialog systems are attracting more and more attention in both academic and industrial communities. In this paper, we survey recent advances and challenges in task-oriented dialog systems. We also discuss three critical topics for task-oriented dialog systems: (1) improving data efficiency to facilitate dialog modeling in low-resource settings, (2) modeling multi-turn dynamics for dialog policy learning to achieve better task-completion performance, and (3) integrating domain ontology knowledge into the dialog model. Besides, we review the recent progresses in dialog evaluation and some widely-used corpora. We believe that this survey, though incomplete, can shed a light on future research in task-oriented dialog systems. task-oriented dialog systems, natural language understanding, dialog policy, dialog state tracking, natural language generation

show abstract

Section: Transfer Learningmentioning

confidence: 99%

Recent advances and challenges in task-oriented dialog systems

Zhang

Takanobu

Huang

et al. 2020

Sci. China Technol. Sci.

105

View full text Add to dashboard Cite

show abstract

“…Persona-based neural conversation models can be categorized into two major research directions. One is to directly train a model from conversational data by considering the persona information (Li et al, 2016b;Kottur et al, 2017;Madotto et al, 2019), while the other approach makes use of the profiles or sideinformation of users to generate the aligned responses (Chu et al, 2018;Qian et al, 2018;Mazare et al, 2018;Song et al, 2019). The work described in this paper belongs to the first research direction.…”

Section: Persona-based Neural Modelsmentioning

confidence: 99%

Guiding Variational Response Generator to Exploit Persona

Wu¹,

Li²,

Wang³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Leveraging persona information of users in Neural Response Generators (NRG) to perform personalized conversations has been considered as an attractive and important topic in the research of conversational agents over the past few years. Despite of the promising progress achieved by recent studies in this field, persona information tends to be incorporated into neural networks in the form of user embeddings, with the expectation that the persona can be involved via End-to-End learning. This paper proposes to adopt the personalityrelated characteristics of human conversations into variational response generators, by designing a specific conditional variational autoencoder based deep model with two new regularization terms employed to the loss function, so as to guide the optimization towards the direction of generating both persona-aware and relevant responses. Besides, to reasonably evaluate the performances of various persona modeling approaches, this paper further presents three direct persona-oriented metrics from different perspectives. The experimental results have shown that our proposed methodology can notably improve the performance of persona-aware response generation, and the metrics are reasonable to evaluate the results. * * Contribution during the internship at Tencent.

show abstract

“…Our prior work (Welch et al, 2019a;Welch et al, 2019b) explored predicting response time, common messages, and author relationships from personal conversation data. Zhang et al (2018) conditioned dialog systems on artificially constructed personas and Madotto et al (2019) used meta-learning to improve this process. Goal-oriented dialog has used demographics (i.e., age, gender) to condition system response generation, showing that this relatively coarse grained personalization improves system performance (Joshi et al, 2017).…”

Section: Related Workmentioning

confidence: 99%

Exploring the Value of Personalized Word Embeddings

Welch

Kummerfeld

Pérez-Rosas

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

In this paper, we introduce personalized word embeddings, and examine their value for language modeling. We compare the performance of our proposed prediction model when using personalized versus generic word representations, and study how these representations can be leveraged for improved performance. We provide insight into what types of words can be more accurately predicted when building personalized models. Our results show that a subset of words belonging to specific psycholinguistic categories tend to vary more in their representations across users and that combining generic and personalized word embeddings yields the best performance, with a 4.7% relative reduction in perplexity. Additionally, we show that a language model using personalized word embeddings can be effectively used for authorship attribution.

show abstract

Personalizing Dialogue Agents via Meta-Learning

Cited by 133 publications

References 31 publications

Recent advances and challenges in task-oriented dialog systems

Recent advances and challenges in task-oriented dialog systems

Guiding Variational Response Generator to Exploit Persona

Exploring the Value of Personalized Word Embeddings

Contact Info

Product

Resources

About