Matthew Henderson

TL;DR: The results suggest that while large improvements on a competitive baseline are possible, trackers are still prone to degradation in mismatched conditions and ensemble learning demonstrates the most accurate tracking can be achieved by combining multiple trackers.

TL;DR: A new wordbased tracking method which maps directly from the speech recognition results to the dialog state without using an explicit semantic decoder is presented, based on a recurrent neural network structure which is capable of generalising to unseen dialog state hypotheses, and which requires very little feature engineering.

TL;DR: This paper reviews this research area, covering both the challenge tasks themselves and summarizing the work they have enabled, including the incorporation of the speech recognition results directly into the dialog state tracker.

TL;DR: The usefulness and wide applicability of the proposed intent detectors are demonstrated, showing that they outperform intent detectors based on fine-tuning the full BERT-Large model or using BERT as a fixed black-box encoder on three diverse intent detection data sets.

TL;DR: Results from the third Dialog State Tracking Challenge are presented, a research community challenge task based on a corpus of annotated logs of human-computer dialogs, with a blind test set evaluation that studied the ability of trackers to generalize to new entities - i.e. new slots and values not present in the training data.