Diversifying dialogue generation with non-conversational text
Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the low-
diversity problem when it comes to open-domain dialogue generation. As bland and generic …
diversity problem when it comes to open-domain dialogue generation. As bland and generic …
Stylized dialogue response generation using stylized unpaired texts
Generating stylized responses is essential to build intelligent and engaging dialogue
systems. However, this task is far from well-explored due to the difficulties of rendering a …
systems. However, this task is far from well-explored due to the difficulties of rendering a …
Unstructured text enhanced open-domain dialogue system: A systematic survey
Incorporating external knowledge into dialogue generation has been proven to benefit the
performance of an open-domain Dialogue System (DS), such as generating informative or …
performance of an open-domain Dialogue System (DS), such as generating informative or …
Polite chatbot: A text style transfer application
Generating polite responses is essential to build intelligent and engaging dialogue systems.
However, this task is far from well-explored due to the difficulties of rendering a particular …
However, this task is far from well-explored due to the difficulties of rendering a particular …
Fundamental exploration of evaluation metrics for persona characteristics of text utterances
C Miyazaki, S Kanno, M Yoda, J Ono… - Proceedings of the …, 2021 - aclanthology.org
To maintain utterance quality of a persona-aware dialog system, inappropriate utterances for
the persona should be thoroughly filtered. When evaluating the appropriateness of a large …
the persona should be thoroughly filtered. When evaluating the appropriateness of a large …
Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models
As large language models (LLMs) become easily accessible nowadays, the trade-off
between safety and helpfulness can significantly impact user experience. A model that …
between safety and helpfulness can significantly impact user experience. A model that …
Improving contextual coherence in variational personalized and empathetic dialogue agents
In recent years, latent variable models, such as the Conditional Variational Auto Encoder
(CVAE), have been applied to both personalized and empathetic dialogue generation. Prior …
(CVAE), have been applied to both personalized and empathetic dialogue generation. Prior …
Conversation and recommendation: knowledge-enhanced personalized dialog system
M He, J Wang, T Ding, T Shen - Knowledge and Information Systems, 2023 - Springer
Traditional recommender systems are usually single-shot systems, lacking real-time dialog
with customers. Using dialog as an interactive method can help capture user preferences …
with customers. Using dialog as an interactive method can help capture user preferences …
Prompting for Socially Intelligent Agents with ChatGPT
Socially Intelligent Agents (SIAs) have become increasingly popular in various contexts,
including education and entertainment. However, creating complex social scenarios tailored …
including education and entertainment. However, creating complex social scenarios tailored …
Deep latent-variable models for text generation
X Shen - arxiv preprint arxiv:2203.02055, 2022 - arxiv.org
Text generation aims to produce human-like natural language output for down-stream tasks.
It covers a wide range of applications like machine translation, document summarization …
It covers a wide range of applications like machine translation, document summarization …