July 29, 2019
We study a conversational reasoning model that strategically traverses through a large-scale common fact knowledge graph (KG) to introduce engaging and contextually diverse entities and attributes. For this study, we collect a new Open-ended Dialog ↔ KG parallel corpus called OpenDialKG, where each utterance from 15K human-to-human role-playing dialogs is manually annotated with ground-truth reference to corresponding entities and paths from a large-scale KG with 1M+ facts. We then propose the DialKG Walker model that learns the symbolic transitions of dialog contexts as structured traversals over KG, and predicts natural entities to introduce given previous dialog contexts via a novel domain-agnostic, attention-based graph path decoder. Automatic and human evaluations show that our model can retrieve more natural and human-like responses than the state-of-the-art baselines or rule-based models, in both in-domain and cross-domain tasks. The proposed model also generates a KG walk path for each entity retrieved, providing a natural way to explain conversational reasoning.
October 16, 2019
Awni Hannun, Adrien Dufraux, Matthijs Douze, Armelle Brun, Emmanuel Vincent
October 16, 2019
July 27, 2019
Pierre-Emmanuel Mazaré, Antoine Bordes, Jason Weston, Braden Hancock
July 27, 2019
June 03, 2019
Adriana Romero Soriano, Dave Meger, Edward Smith, Scott Fujimoto
June 03, 2019
May 29, 2019
Douwe Kiela, Abi See, Jason Weston, Stephen Roller
May 29, 2019
December 04, 2018
Sebastian Schuster, Sonal Gupta, Rushin Shah, Mike Lewis
December 04, 2018
December 13, 2019
Adrien Dufraux, Emmanuel Dupoux, Awni Hannun, Armelle Brun, Matthijs Douze
December 13, 2019
July 28, 2019
Abigail See, Stephen Roller, Douwe Kiela, Jason Weston
July 28, 2019
November 05, 2019
Shane Moon, Pararth Shah, Anuj Kumar, Rajen Subba
November 05, 2019
Product experiences
Foundational models
Product experiences
Latest news
Foundational models