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

Olabiyi, O.; Khazane, Anish; Mueller, Erik T.

doi:10.1109/icmla.2018.00079

Cited by 7 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

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

Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks

Tian

Zhang

et al. 2021

AAAI

View full text Add to dashboard Cite

Personalized conversation models (PCMs) generate responses according to speaker preferences. Existing personalized conversation tasks typically require models to extract speaker preferences from user descriptions or their conversation histories, which are scarce for newcomers and inactive users. In this paper, we propose a few-shot personalized conversation task with an auxiliary social network. The task requires models to generate personalized responses for a speaker given a few conversations from the speaker and a social network. Existing methods are mainly designed to incorporate descriptions or conversation histories. Those methods can hardly model speakers with so few conversations or connections between speakers. To better cater for newcomers with few resources, we propose a personalized conversation model (PCM) that learns to adapt to new speakers as well as enabling new speakers to learn from resource-rich speakers. Particularly, based on a meta-learning based PCM, we propose a task aggregator (TA) to collect other speakers' information from the social network. The TA provides prior knowledge of the new speaker in its meta-learning. Experimental results show our methods outperform all baselines in appropriateness, diversity, and consistency with speakers.

show abstract

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%

Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks

Tian

Zhang

et al. 2021

AAAI

View full text Add to dashboard Cite

show abstract

“…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%

“…Knowing information about a speaker, such as her linguistic style or personal information can help predict her response, and knowing more about both speakers 1 https://github.com/NoSyu/VHUCM from their previous conversations can help predict the contents of their conversation. Some recent work models the speakers in addition to the utterances (Li et al, 2016b;Olabiyi et al, 2018), but these models tend to overly emphasize the speaker such that they generate very similar responses even when the previous utterances are different. Another difficult and under-tackled problem in conversation response generation is the cold start problem, when the training data do not contain one or both of the speakers.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Variational Hierarchical User-based Conversation Model

Bak¹,

Oh²

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Generating appropriate conversation responses requires careful modeling of the utterances and speakers together. Some recent approaches to response generation model both the utterances and the speakers, but these approaches tend to generate responses that are overly tailored to the speakers. To overcome this limitation, we propose a new model with a stochastic variable designed to capture the speaker information and deliver it to the conversational context. An important part of this model is the network of speakers in which each speaker is connected to one or more conversational partner, and this network is then used to model the speakers better. To test whether our model generates more appropriate conversation responses, we build a new conversation corpus containing approximately 27,000 speakers and 770,000 conversations. With this corpus, we run experiments of generating conversational responses and compare our model with other state-of-the-art models. By automatic evaluation metrics and human evaluation, we show that our model outperforms other models in generating appropriate responses. An additional advantage of our model is that it generates better responses for various new user scenarios, for example when one of the speakers is a known user in our corpus but the partner is a new user. For replicability, we make available all our code and data 1 .

show abstract

Business chatbots with deep learning technologies: state-of-the-art, taxonomies, and future research directions

Zhang,

Lau,

David Xu

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

With the support of advanced hardware and software technology, Artificial Intelligence (AI) techniques, especially the increasing number of deep learning algorithms, have spawned the popularization of online intelligent services and accelerated the contemporary development and applications of chatbot systems. The promise of providing 24/7 uninterrupted business services and minimizing workforce costs has made business chatbots a hot topic due to the impact of the pandemic. It has attracted considerable attention from academic researchers and business practitioners. However, a thorough technical review of advanced chatbot technologies and their relevance and applications to various business domains is rare in the literature. The main contribution of this review article is the critical analysis of various chatbot development approaches and the underlying deep learning computational methods in the context of some business applications. We first conceptualize current business chatbot architectures and illustrate the technical characteristics of two common structures. Next, we explore the mainstream deep learning technologies in chatbot design from the perspective of computational methods and usages. Then, we propose a new framework to classify chatbot construction architectures and differentiate the traditional retrieval-based and generation-based chatbots in terms of the modern pipeline and end-to-end structures. Finally, we highlight future research directions for business chatbots to enable researchers to devote their efforts to the most promising research topics and commercial scenarios and for practitioners to benefit from realizing the trend in business chatbot development and applications.

show abstract

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

Cited by 7 publications

References 11 publications

Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks

Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks

Variational Hierarchical User-based Conversation Model

Business chatbots with deep learning technologies: state-of-the-art, taxonomies, and future research directions

Contact Info

Product

Resources

About