[HTML][HTML] Pre-trained language models and their applications
Pre-trained language models have achieved striking success in natural language
processing (NLP), leading to a paradigm shift from supervised learning to pre-training …
processing (NLP), leading to a paradigm shift from supervised learning to pre-training …
Conversational information seeking
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 …
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
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 …
The workshop explored the current state of the art along with its limitations and suggested …
Godel: Large-scale pre-training for goal-directed dialog
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 …
language model for dialog. In contrast with earlier models such as DialoGPT, GODEL …
Plato-2: Towards building an open-domain chatbot via curriculum learning
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 …
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
Next generation task-oriented dialog systems need to understand conversational contexts
with their perceived surroundings, to effectively help users in the real-world multimodal …
with their perceived surroundings, to effectively help users in the real-world multimodal …
Plato-xl: Exploring the large-scale pre-training of dialogue generation
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 …
with up to 11 billion parameters, trained on both Chinese and English social media …
A comprehensive assessment of dialog evaluation metrics
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 …
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
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 …
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
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 …
minimal human efforts is a long-standing challenge in dialog research. Recently large …