Improved Deep Learning Baselines for Ubuntu Corpus Dialogs
This work provides improved baselines for researchers working on multi-turn dialog systems using the largest publicly available corpus.
The authors tackled next utterance ranking on the Ubuntu Dialog Corpus by evaluating various deep learning models and creating an ensemble, achieving state-of-the-art performance on this dataset.
This paper presents results of our experiments for the next utterance ranking on the Ubuntu Dialog Corpus -- the largest publicly available multi-turn dialog corpus. First, we use an in-house implementation of previously reported models to do an independent evaluation using the same data. Second, we evaluate the performances of various LSTMs, Bi-LSTMs and CNNs on the dataset. Third, we create an ensemble by averaging predictions of multiple models. The ensemble further improves the performance and it achieves a state-of-the-art result for the next utterance ranking on this dataset. Finally, we discuss our future plans using this corpus.