Improved Deep Learning Baselines for Ubuntu Corpus Dialogs

TL;DR

This paper evaluates and improves deep learning models for next utterance ranking in the Ubuntu Dialog Corpus, achieving state-of-the-art results through model evaluation and ensemble techniques.

Contribution

It provides an independent evaluation of existing models, compares various neural architectures, and introduces an ensemble approach to enhance performance.

Findings

Ensemble models outperform individual models.

Achieved state-of-the-art ranking performance.

Evaluated multiple neural network architectures.

Abstract

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.