Language models demonstrate both quantitative improvement and new qualitative
capabilities with increasing scale. Despite their potentially transformative impact, these new …

Despite showing increasingly human-like conversational abilities, state-of-the-art dialogue
models often suffer from factual incorrectness and hallucination of knowledge (Roller et al …

Recent development in NLP shows a strong trend towards refining pre-trained models with a
domain-specific dataset. This is especially the case for response generation where emotion …

We survey human evaluation in papers presenting work on creative natural language
generation that have been published in INLG 2020 and ICCC 2020. The most typical human …

Existing knowledge-grounded dialogue systems typically use finetuned versions of a
pretrained language model (LM) and large-scale knowledge bases. These models typically …

Target-guided response generation enables dialogue systems to smoothly transition a
conversation from a dialogue context toward a target sentence. Such control is useful for …

Incorporating external knowledge into dialogue generation has been proven to benefit the
performance of an open-domain Dialogue System (DS), such as generating informative or …

Building open domain conversational systems that allow users to have engaging
conversations on topics of their choice is a challenging task. The Alexa Prize Socialbot …

In this work we develop a fully data driven conversational agent capable of carrying out
motivational coaching sessions in Spanish, French, Norwegian, and English. Unlike the …

Existing knowledge-grounded open-domain dialogue generation models often face the
hallucination problem, ie the dialogue generative model will persist in an inappropriate …