Results 21 to 30 of about 651,687 (315)

SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations [PDF]

open access: yesConference 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

DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation [PDF]

open access: yesAnnual 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

Towards Identifying Social Bias in Dialog Systems: Framework, Dataset, and Benchmark [PDF]

open access: yesConference 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

Dialogical Theology and Dialogical Practice

open access: yesScriptura, 2022
This article focuses on the relationship between religions and dialogue, considering its current relevance. It shows how interreligious dialogue forms the basis for a pluralised theology. Against the backdrop of the established research project ‘Religions and Dialogue in Modern Societies’ (ReDi), we find an integrative approach to interreligious ...
Weisse, Wolfram, Meir, Ephraim
openaire   +2 more sources

Challenges in Building Intelligent Open-domain Dialog Systems [PDF]

open access: yesACM 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]

open access: yesConference 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

What is effective classroom dialog? A comparative study of classroom dialog in Chinese expert and novice mathematics teachers’ classrooms

open access: yesFrontiers in Psychology, 2022
Conducting effective classroom dialog is an important foundation for high-quality classrooms. This study investigates the characteristics of effective classroom dialog from the perspective of Chinese mathematics classrooms.
Wenjun Zhao, Jing Ma, Yiming Cao
doaj   +1 more source

SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding [PDF]

open access: yesInternational Conference on Computational Linguistics, 2022
Pre-training methods with contrastive learning objectives have shown remarkable success in dialog understanding tasks. However, current contrastive learning solely considers the self-augmented dialog samples as positive samples and treats all other ...
Wanwei He   +8 more
semanticscholar   +1 more source

BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog [PDF]

open access: yesNAACL-HLT, 2022
A typical end-to-end task-oriented dialog system transfers context into dialog state, and upon which generates a response, which usually faces the problem of error propagation from both previously generated inaccurate dialog states and responses ...
Haipeng Sun   +3 more
semanticscholar   +1 more source

What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition

open access: yesTransactions of the Association for Computational Linguistics, 2021
Dialog acts can be interpreted as the atomic units of a conversation, more fine-grained than utterances, characterized by a specific communicative function.
Piotr Żelasko   +2 more
doaj   +1 more source

Home - About - Disclaimer - Privacy