Results 21 to 30 of about 679,813 (367)
Few-shot Natural Language Generation for Task-Oriented Dialog [PDF]
Findings, 2020 As a crucial component in task-oriented dialog systems, the Natural Language Generation (NLG) module converts a dialog act represented in a semantic form into a response in natural language. The success of traditional template-based or statistical models
Baolin Peng +6 more
semanticscholar +1 more source
UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2 [PDF]
AAAI Conference on Artificial Intelligence, 2020 This paper presents our task-oriented dialog system UBAR which models task-oriented dialogs on a dialog session level. Specifically, UBAR is acquired by fine-tuning the large pre-trained unidirectional language model GPT-2 on the sequence of the entire ...
Yunyi Yang, Yunhao Li, Xiaojun Quan
semanticscholar +1 more source
Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders [PDF]
Annual Meeting of the Association for Computational Linguistics, 2017 While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses.
Tiancheng Zhao, Ran Zhao, M. Eskénazi
semanticscholar +1 more source
A Comprehensive Assessment of Dialog Evaluation Metrics [PDF]
EANCS, 2021 Automatic evaluation metrics are a crucial component of dialog systems research. Standard language evaluation metrics are known to be ineffective for evaluating dialog. As such, recent research has proposed a number of novel, dialog-specific metrics that
Yi-Ting Yeh, M. Eskénazi, Shikib Mehri
semanticscholar +1 more source
Towards Knowledge-Based Recommender Dialog System [PDF]
Conference on Empirical Methods in Natural Language Processing, 2019 In this paper, we propose a novel end-to-end framework called KBRD, which stands for Knowledge-Based Recommender Dialog System. It integrates the recommender system and the dialog generation system.
Qibin Chen +6 more
semanticscholar +1 more source
DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation [PDF]
Annual Meeting of the Association for Computational Linguistics, 2022 Dialog response generation in open domain is an important research topic where the main challenge is to generate relevant and diverse responses. In this paper, we propose a new dialog pre-training framework called DialogVED, which introduces continuous ...
Wei Chen +11 more
semanticscholar +1 more source
SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations [PDF]
Conference on Empirical Methods in Natural Language Processing, 2021 Next generation task-oriented dialog systems need to understand conversational contexts with their perceived surroundings, to effectively help users in the real-world multimodal environment.
Satwik Kottur +3 more
semanticscholar +1 more source
Towards Identifying Social Bias in Dialog Systems: Framework, Dataset, and Benchmark [PDF]
Conference on Empirical Methods in Natural Language Processing, 2022 The research of open-domain dialog systems has been greatly prospered by neural models trained on large-scale corpora, however, such corpora often introduce various safety problems (e.g., offensive languages, biases, and toxic behaviors) that ...
Jingyan Zhou +8 more
semanticscholar +1 more source
Challenges in Building Intelligent Open-domain Dialog Systems [PDF]
ACM Trans. Inf. Syst., 2019 There is a resurgent interest in developing intelligent open-domain dialog systems due to the availability of large amounts of conversational data and the recent progress on neural approaches to conversational AI [33].
Minlie Huang, Xiaoyan Zhu, Jianfeng Gao
semanticscholar +1 more source
INSPIRED: Toward Sociable Recommendation Dialog Systems [PDF]
Conference on Empirical Methods in Natural Language Processing, 2020 In recommendation dialogs, humans commonly disclose their preference and make recommendations in a friendly manner. However, this is a challenge when developing a sociable recommendation dialog system, due to the lack of dialog dataset annotated with ...
Shirley Anugrah Hayati +4 more
semanticscholar +1 more source