In this work, we introduce the tasks of extracting and inferring personal attributes from human-human dialogue.
We propose a shared task on training instance selection for few-shot neural text generation.
Neural natural language generation (NLG) and understanding (NLU) models are data-hungry and require massive amounts of annotated data to be competitive.
We present a lightweight annotation tool, the Data AnnotatoR Tool (DART), for the general task of labeling structured data with textual descriptions.
In this work, we extend the task oriented LU problem to human-to-human (H2H) conversations, focusing on the slot tagging task.
Slot tagging, the task of detecting entities in input user utterances, is a key component of natural language understanding systems for personal digital assistants.
no code implementations • • Paul Crook, Alex Marin, Vipul Agarwal, Khushboo Aggarwal, Tasos Anastasakos, Ravi Bikkula, Daniel Boies, Asli Celikyilmaz, Ch, Senthilkumar ramohan, Zhaleh Feizollahi, Roman Holenstein, Minwoo Jeong, Omar Khan, Young-Bum Kim, Elizabeth Krawczyk, Xiaohu Liu, Danko Panic, Vasiliy Radostev, Nikhil Ramesh, Jean-Phillipe Robichaud, Alex Rochette, re, Logan Stromberg, Ruhi Sarikaya