[HTML][HTML] Pre-trained language models and their applications

H Wang, J Li, H Wu, E Hovy, Y Sun - Engineering, 2023‏ - Elsevier
Pre-trained language models have achieved striking success in natural language
processing (NLP), leading to a paradigm shift from supervised learning to pre-training …

Conversational information seeking

H Zamani, JR Trippas, J Dalton… - … and Trends® in …, 2023‏ - nowpublishers.com
Conversational information seeking (CIS) is concerned with a sequence of interactions
between one or more users and an information system. Interactions in CIS are primarily …

Report from the nsf future directions workshop on automatic evaluation of dialog: Research directions and challenges

S Mehri, J Choi, LF D'Haro, J Deriu, M Eskenazi… - arxiv preprint arxiv …, 2022‏ - arxiv.org
This is a report on the NSF Future Directions Workshop on Automatic Evaluation of Dialog.
The workshop explored the current state of the art along with its limitations and suggested …

Godel: Large-scale pre-training for goal-directed dialog

B Peng, M Galley, P He, C Brockett, L Liden… - arxiv preprint arxiv …, 2022‏ - arxiv.org
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 …

Plato-2: Towards building an open-domain chatbot via curriculum learning

S Bao, H He, F Wang, H Wu, H Wang, W Wu… - arxiv preprint arxiv …, 2020‏ - arxiv.org
To build a high-quality open-domain chatbot, we introduce the effective training process of
PLATO-2 via curriculum learning. There are two stages involved in the learning process. In …

SIMMC 2.0: A task-oriented dialog dataset for immersive multimodal conversations

S Kottur, S Moon, A Geramifard… - arxiv preprint arxiv …, 2021‏ - arxiv.org
Next generation task-oriented dialog systems need to understand conversational contexts
with their perceived surroundings, to effectively help users in the real-world multimodal …

Plato-xl: Exploring the large-scale pre-training of dialogue generation

S Bao, H He, F Wang, H Wu, H Wang, W Wu… - arxiv preprint arxiv …, 2021‏ - arxiv.org
To explore the limit of dialogue generation pre-training, we present the models of PLATO-XL
with up to 11 billion parameters, trained on both Chinese and English social media …

A comprehensive assessment of dialog evaluation metrics

YT Yeh, M Eskenazi, S Mehri - arxiv preprint arxiv:2106.03706, 2021‏ - arxiv.org
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 …

Conversations are not flat: Modeling the dynamic information flow across dialogue utterances

Z Li, J Zhang, Z Fei, Y Feng, J Zhou - arxiv preprint arxiv:2106.02227, 2021‏ - arxiv.org
Nowadays, open-domain dialogue models can generate acceptable responses according to
the historical context based on the large-scale pre-trained language models. However, they …

Sgp-tod: Building task bots effortlessly via schema-guided llm prompting

X Zhang, B Peng, K Li, J Zhou, H Meng - arxiv preprint arxiv:2305.09067, 2023‏ - arxiv.org
Building end-to-end task bots and maintaining their integration with new functionalities using
minimal human efforts is a long-standing challenge in dialog research. Recently large …