The Design and Implementation of XiaoIce, an Empathetic Social Chatbot

By Adrian Choi. 2020

Subfields: Natural Language Processing, LLM Agents & Tool Use

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Jason Aaron Edward Weston
2. Kurt Shuster
3. Y-Lan Boureau
4. Eric Michael Smith
5. Emily Dinan
6. Arthur Szlam
7. Da Ju
8. Stephen Roller

In LLM Agents & Tool Use

1. Jason Aaron Edward Weston
2. Arthur Szlam

Citations in the corpus

• Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions (2020, methodology): “Some commonly used wordoverlap metrics include F1 (Rajpurkar et al., 2016), BLEU (Papineni et al., 2002; Li et al., 2017c), ROUGE (Lin, 2004; Fan et al., 2019), CIDEr (Vedantam, Zitnick, and Parikh, 2015; Zhou et al., 2020), and METEOR (Banerjee and Lavie, 2005; Zhou et al., 2020).”
• Hierarchical Reinforcement Learning for Open-Domain Dialog (2019, result): “Because users can choose to chat as long as they like with any particular bot, we also measure chat length as a sign of engagement, following prior work (Zhou et al. 2018).”