Results 11 to 20 of about 679,813 (367)
Towards Emotional Support Dialog Systems [PDF]
Annual Meeting of the Association for Computational Linguistics, 2021 Emotional support is a crucial ability for many conversation scenarios, including social interactions, mental health support, and customer service chats.
Siyang Liu +7 more
semanticscholar +1 more source
Opportunities and Challenges in Neural Dialog Tutoring [PDF]
Conference of the European Chapter of the Association for Computational Linguistics, 2023 Designing dialog tutors has been challenging as it involves modeling the diverse and complex pedagogical strategies employed by human tutors. Although there have been significant recent advances in neural conversational systems using large language ...
Jakub Macina +6 more
semanticscholar +1 more source
GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection [PDF]
AAAI Conference on Artificial Intelligence, 2021 Pre-trained models have proved to be powerful in enhancing task-oriented dialog systems. However, current pre-training methods mainly focus on enhancing dialog understanding and generation tasks while neglecting the exploitation of dialog policy. In this
Wanwei He +11 more
semanticscholar +1 more source
USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation [PDF]
Annual Meeting of the Association for Computational Linguistics, 2020 The lack of meaningful automatic evaluation metrics for dialog has impeded open-domain dialog research. Standard language generation metrics have been shown to be ineffective for evaluating dialog models.
Shikib Mehri, M. Eskénazi
semanticscholar +1 more source
Talk-to-Edit: Fine-Grained Facial Editing via Dialog [PDF]
IEEE International Conference on Computer Vision, 2021 Facial editing is an important task in vision and graphics with numerous applications. However, existing works are incapable to deliver a continuous and fine-grained editing mode (e.g., editing a slightly smiling face to a big laughing one) with natural ...
Yuming Jiang +4 more
semanticscholar +1 more source
GODEL: Large-Scale Pre-Training for Goal-Directed Dialog [PDF]
arXiv.org, 2022 We introduce GODEL (Grounded Open Dialogue Language Model), a large pre-trained language model for dialog. In contrast with earlier models such as DialoGPT, GODEL leverages a new phase of grounded pre-training designed to better support adapting GODEL to
Baolin Peng +8 more
semanticscholar +1 more source
TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking [PDF]
SIGDIAL Conferences, 2020 Task-oriented dialog systems rely on dialog state tracking (DST) to monitor the user’s goal during the course of an interaction. Multi-domain and open-vocabulary settings complicate the task considerably and demand scalable solutions.
Michael Heck +6 more
semanticscholar +1 more source
Dialog Inpainting: Turning Documents into Dialogs [PDF]
International Conference on Machine Learning, 2022 Many important questions (e.g."How to eat healthier?") require conversation to establish context and explore in depth. However, conversational question answering (ConvQA) systems have long been stymied by scarce training data that is expensive to collect.
Zhuyun Dai +6 more
semanticscholar +1 more source
Unsupervised Evaluation of Interactive Dialog with DialoGPT [PDF]
SIGDIAL Conferences, 2020 It is important to define meaningful and interpretable automatic evaluation metrics for open-domain dialog research. Standard language generation metrics have been shown to be ineffective for dialog.
Shikib Mehri, M. Eskénazi
semanticscholar +1 more source
Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation [PDF]
Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2022 Recently, pre-training methods have shown remarkable success in task-oriented dialog (TOD) systems. However, most existing pre-trained models for TOD focus on either dialog understanding or dialog generation, but not both. In this paper, we propose SPACE,
Wanwei He +6 more
semanticscholar +1 more source