Improved Deep Learning Baselines for Ubuntu Corpus Dialogs

2015/10/13 by Rudolf Kadlec, Martin Schmid, Kadlec, Rudolf +3 · 6 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #ICT in Developing Communities #Speech and dialogue systems #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.1510.03753

Accepted to Machine Learning for SLU & Interaction NIPS 2015 Workshop

openalex publication_date 2015/10/13 · arxiv created 2015/11/03 · arxiv updated 2015/11/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• A Neural Conversational Model
• Theano: new features and speed improvements
• Long Short-Term Memory
• Gradient-based learning applied to document recognition
• Bidirectional recurrent neural networks
• Convolutional Neural Networks for Sentence Classification

Cited by

• Context-Aware Dialog Re-Ranking for Task-Oriented Dialog Systems
• Dialogue-oriented Pre-training
• Sequential Sentence Matching Network for Multi-turn Response Selection in Retrieval-based Chatbots
• NE-Table: A Neural key-value table for Named Entities
• Multi-turn Dialogue Reading Comprehension with Pivot Turns and Knowledge
• A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots

Related

• The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems
• Enhance word representation for out-of-vocabulary on Ubuntu dialogue corpus
• Learning Multi-Party Turn-Taking Models from Dialogue Logs
• Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding
• On the Evaluation of Dialogue Systems with Next Utterance Classification