• Publications
  • Influence
ChID: A Large-scale Chinese IDiom Dataset for Cloze Test
TLDR
A large-scale Chinese cloze test dataset ChID is proposed, which studies the comprehension of idiom, a unique language phenomenon in Chinese, in which the idioms in a passage are replaced by blank symbols and the correct answer needs to be chosen from well-designed candidate idioms.
KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation
TLDR
This paper proposes a Chinese multi-domain knowledge-driven conversation dataset, KdConv, which grounds the topics in multi-turn conversations to knowledge graphs, and provides several benchmark models to facilitate the following research.
Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation
TLDR
Automatic, human observational, and interactive evaluation shows that the proposed difference-aware knowledge selection method is able to select knowledge more accurately and generate more informative responses, significantly outperforming the state-of-the-art baselines.
Towards Emotional Support Dialog Systems
TLDR
The Emotional Support Conversation task is defined and an ESC Framework is proposed, which is grounded on the Helping Skills Theory, to show the importance of support strategies in providing effective emotional support and the utility of ESConv in training more emotional support systems.
On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark
TLDR
A dialogue safety classifier is trained to provide a strong baseline for context-sensitive dialogue unsafety detection, and a taxonomy for dialogue safety specifically designed to capture unsafe behaviors in human-bot dialogue settings is proposed.
EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training
TLDR
EVA, a Chinese dialogue system that contains the largest Chinese pre-trained dialogue model with 2.8B parameters is proposed, and extensive experiments on automatic and human evaluation show that EVA outperforms other ChinesePre- trained dialogue models especially in the multi-turn interaction of humanbot conversations.
Exploring Prompt-based Few-shot Learning for Grounded Dialog Generation
TLDR
The potential of prompt-based methods in few-shot learning for grounded dialog generation for GDG is demonstrated and directions of improvement for future work are provided.
CEM: Commonsense-aware Empathetic Response Generation
TLDR
This work proposes a novel approach for empathetic response generation, which leverages commonsense to draw more information about the user’s situation and uses this additional information to further enhance the empathy expression in generated responses.
EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training
TLDR
Automatic and human evaluations show that the proposed EVA2.0 is the largest opensource Chinese dialogue model with 2.8 billion parameters and significantly outperforms other open-source counterparts.
CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation
TLDR
A multi-factor hierarchical framework, CoMAE, is proposed, which models the above three key factors of empathy expression in a hierarchical way and can generate more empathetic responses than previous methods.
...
1
2
...