1 code implementation • ICML 2018 • Ondrej Bajgar, Rudolf Kadlec, Jan Kleindienst
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.
no code implementations • WS 2017 • Rudolf Kadlec, Ondrej Bajgar, Jan Kleindienst
Many papers have been published on the knowledge base completion task in the past few years.
no code implementations • EACL 2017 • Miroslav Vodolán, Rudolf Kadlec, Jan Kleindienst
This paper presents a hybrid dialog state tracker enhanced by trainable Spoken Language Understanding (SLU) for slot-filling dialog systems.
2 code implementations • 4 Oct 2016 • Ondrej Bajgar, Rudolf Kadlec, Jan Kleindienst
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.
2 code implementations • ACL 2016 • Rudolf Kadlec, Martin Schmid, Ondrej Bajgar, Jan Kleindienst
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)
Machine Reading Comprehension Open-Domain Question Answering
no code implementations • 13 Oct 2015 • Miroslav Vodolán, Rudolf Kadlec, Jan Kleindienst
This paper presents a hybrid dialog state tracker that combines a rule based and a machine learning based approach to belief state tracking.
no code implementations • 13 Oct 2015 • Rudolf Kadlec, Martin Schmid, Jan Kleindienst
The ensemble further improves the performance and it achieves a state-of-the-art result for the next utterance ranking on this dataset.