Hybrid Code Networks using a convolutional neural network as an input\n layer achieves higher turn accuracy

2019/07/28 by Petr Marek, Marek, Petr
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1907.12162

openalex publication_date 2019/07/28 · openalex created_date 2022/07/28 · openalex updated_date 2026/07/28

Abstract

The dialogue management is a task of conversational artificial intelligence.\nThe goal of the dialogue manager is to select the appropriate response to the\nconversational partner conditioned by the input message and recent dialogue\nstate. Hybrid Code Networks is one of the models of dialogue managers, which\nuses an average of word embeddings and bag-of-words as input features. We\nperform experiments on Dialogue bAbI Task 6 and Alquist Conversational Dataset.\nThe experiments show that the convolutional neural network used as an input\nlayer of the Hybrid Code Network improves the model's turn accuracy.\n

Citations

• A Neural Conversational Model
• Long Short-Term Memory
• Learning End-to-End Goal-Oriented Dialog
• Convolutional Neural Networks for Sentence Classification

Related

• Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
• Improving Robustness of Neural Dialog Systems in a Data-Efficient Way with Turn Dropout
• Multi-turn Response Selection with Commonsense-enhanced Language Models
• Generative Deep Neural Networks for Dialogue: A Short Review
• Teaching Machines to Converse