December 4, 2018
Semantic parsing using hierarchical representations has recently been proposed for task oriented dialog with promising results. In this paper, we present three different improvements to the model: contextualized embeddings, ensembling, and pairwise re-ranking based on a language model. We taxonomize the errors possible for the hierarchical representation, such as wrong top intent, missing spans or split spans, and show that the three approaches correct different kinds of errors. The best model combines the three techniques and gives 6.4% better exact match accuracy than the state-of-the-art, with an error reduction of 33%, resulting in a new state-of-the-art result on the Task Oriented Parsing (TOP) dataset.
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
Foundational models
Latest news
Foundational models