Improved Deep Learning Baselines for Ubuntu Corpus Dialogs

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.

Accepted to Machine Learning for SLU & Interaction NIPS 2015 Workshop

References in corpus (4)

• Convolutional Neural Networks for Sentence Classification
• Theano: new features and speed improvements
• Blocks and Fuel: Frameworks for deep learning
• Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews

Cited by in corpus (28)

• A Survey of Available Corpora for Building Data-Driven Dialogue Systems
• Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
• Modeling Multi-turn Conversation with Deep Utterance Aggregation
• Conversational Contextual Cues: The Case of Personalization and History for Response Ranking
• Lingke: A Fine-grained Multi-turn Chatbot for Customer Service
• Sequential Attention-based Network for Noetic End-to-End Response Selection
• Enhance word representation for out-of-vocabulary on Ubuntu dialogue corpus
• Sentence Pair Scoring: Towards Unified Framework for Text Comprehension
• Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots
• Deep Retrieval-Based Dialogue Systems: A Short Review
• Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots
• A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
• Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding
• Knowledge-incorporating ESIM models for Response Selection in Retrieval-based Dialog Systems
• The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection
• Topic-Aware Multi-turn Dialogue Modeling
• Dialogue-oriented Pre-training
• Advances in Multi-turn Dialogue Comprehension: A Survey
• A Bi-Encoder LSTM Model For Learning Unstructured Dialogs
• Multi-turn Dialogue Reading Comprehension with Pivot Turns and Knowledge
• Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots
• Learning Multi-Level Information for Dialogue Response Selection by Highway Recurrent Transformer
• Context-Aware Dialog Re-Ranking for Task-Oriented Dialog Systems
• "None of the Above":Measure Uncertainty in Dialog Response Retrieval
• Sequential Sentence Matching Network for Multi-turn Response Selection in Retrieval-based Chatbots
• Improving Matching Models with Hierarchical Contextualized Representations for Multi-turn Response Selection
• Multi-Granularity Representations of Dialog
• NE-Table: A Neural key-value table for Named Entities