BYU-EVE: Mixed Initiative Dialog via Structured Knowledge Graph Traversal and Conversational Scaffolding

By Nancy Fulda, Tyler Etchart, William Myers, Daniel Ricks, Zachary Brown, Joseph Szendre, Ben Murdoch, Andrew N. Carr, David Wingate. 2018

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. Emily Dinan
2. Y-Lan Boureau
3. Jason Aaron Edward Weston
4. Gavin Abercrombie
5. Dirk Hovy
6. Shannon L. Spruit
7. Dilek Z. Hakkani-Tür
8. Verena Rieser

Citations in the corpus

• Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling (2021, background): “Generally focusing on user input, rather than system-generated responses, most offensive language detection for dialog relies on identification of keywords (Cercas Curry et al., 2018; Fulda et al., 2018; Khatri et al., 2018; Paranjape et al., 2020).”
• Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design (2022, background): “Existing work on conversational systems often relies on identification of keywords (Ram et al., 2017; Cercas Curry et al., 2018; Fulda et al., 2018; Khatri et al., 2018; Paranjape et al., 2020), or uses human labels such as flagging of a post to train classifiers (Larionov et al.”
• Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize (2018, background): “Eve (Fulda et al., 2018) tried to create sensitive detection models that utilizes context.”