If future AI systems are to be reliably safe in novel situations, they will need to incorporate general principles guiding them to robustly recognize which outcomes and behaviours would be harmful.
no code implementations • 17 Oct 2019 • Christian Muise, Tathagata Chakraborti, Shubham Agarwal, Ondrej Bajgar, Arunima Chaudhary, Luis A. Lastras-Montano, Josef Ondrej, Miroslav Vodolan, Charlie Wiecha
Generating complex multi-turn goal-oriented dialogue agents is a difficult problem that has seen a considerable focus from many leaders in the tech industry, including IBM, Google, Amazon, and Microsoft.
no code implementations • 2 Feb 2019 • Adi Botea, Christian Muise, Shubham Agarwal, Oznur Alkan, Ondrej Bajgar, Elizabeth Daly, Akihiro Kishimoto, Luis Lastras, Radu Marinescu, Josef Ondrej, Pablo Pedemonte, Miroslav Vodolan
Dialogue systems have many applications such as customer support or question answering.
We point out important problems with the common practice of using the best single model performance for comparing deep learning architectures, and we propose a method that corrects these flaws.
We show that training on the new data improves the accuracy of our Attention-Sum Reader model on the original CBT test data by a much larger margin than many recent attempts to improve the model architecture.
Several large cloze-style context-question-answer datasets have been introduced recently: the CNN and Daily Mail news data and the Children's Book Test.
Ranked #5 on Open-Domain Question Answering on SearchQA (Unigram Acc metric)