Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems

Abstract

Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and stylised responses without the natural variation of human language. They are also not easily scaled to systems covering multiple domains and languages. This paper presents a statistical language generator based on a semantically controlled Long Short-term Memory (LSTM) structure. The LSTM generator can learn from unaligned data by jointly optimising sentence planning and surface realisation using a simple cross entropy training criterion, and language variation can be easily achieved by sampling from output candidates. With fewer heuristics, an objective evaluation in two differing test domains showed the proposed method improved performance compared to previous methods. Human judges scored the LSTM system higher on informativeness and naturalness and overall preferred it to the other systems.

To be appear in EMNLP 2015

References in corpus (5)

• Sequence to Sequence Learning with Neural Networks
• Recurrent Neural Network Regularization
• Theano: new features and speed improvements
• Deep Visual-Semantic Alignments for Generating Image Descriptions
• Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking

Cited by in corpus (60)

• Deep Reinforcement Learning: An Overview
• An Algorithmic Perspective on Imitation Learning
• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
• A Neural Network Architecture Combining Gated Recurrent Unit (GRU) and Support Vector Machine (SVM) for Intrusion Detection in Network Traffic Data
• Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
• A Persona-Based Neural Conversation Model
• A Network-based End-to-End Trainable Task-oriented Dialogue System
• A Simple Language Model for Task-Oriented Dialogue
• Toward Controlled Generation of Text
• Style Transfer as Unsupervised Machine Translation
• Continuously Learning Neural Dialogue Management
• Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks
• Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-Art
• Context-aware Natural Language Generation with Recurrent Neural Networks
• Multi-Task Learning for Speaker-Role Adaptation in Neural Conversation Models
• A Context-aware Natural Language Generator for Dialogue Systems
• Controlling Output Length in Neural Encoder-Decoders
• Revisiting Activation Regularization for Language RNNs
• Topic-based Evaluation for Conversational Bots
• Implicit Distortion and Fertility Models for Attention-based Encoder-Decoder NMT Model
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• An Attentional Neural Conversation Model with Improved Specificity
• Neural Enquirer: Learning to Query Tables with Natural Language
• MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance
• Neural Personalized Response Generation as Domain Adaptation
• Referenceless Quality Estimation for Natural Language Generation
• Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning
• Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability
• Steering Output Style and Topic in Neural Response Generation
• Building a Neural Semantic Parser from a Domain Ontology
• Show Us the Way: Learning to Manage Dialog from Demonstrations
• Semantic Refinement GRU-based Neural Language Generation for Spoken Dialogue Systems
• Reference-Aware Language Models
• Reasoning about Actions and State Changes by Injecting Commonsense Knowledge
• Log-Linear RNNs: Towards Recurrent Neural Networks with Flexible Prior Knowledge
• Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding
• Lifelong Language Knowledge Distillation
• Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game
• Direct Output Connection for a High-Rank Language Model
• Boosting Naturalness of Language in Task-oriented Dialogues via Adversarial Training
• How to Build User Simulators to Train RL-based Dialog Systems
• NeuronBlocks: Building Your NLP DNN Models Like Playing Lego
• Low-Rank RNN Adaptation for Context-Aware Language Modeling
• Characterizing Variation in Crowd-Sourced Data for Training Neural Language Generators to Produce Stylistically Varied Outputs
• Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation
• ViDA-MAN: Visual Dialog with Digital Humans
• Learning an Executable Neural Semantic Parser
• Dialogue Act Classification in Group Chats with DAG-LSTMs
• Neural MultiVoice Models for Expressing Novel Personalities in Dialog
• Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation
• Natural Language Generation Using Link Grammar for General Conversational Intelligence
• A Bi-Encoder LSTM Model For Learning Unstructured Dialogs
• Towards Content Transfer through Grounded Text Generation
• Learning End-to-End Goal-Oriented Dialog with Multiple Answers
• Game-Based Video-Context Dialogue
• Discourse Embellishment Using a Deep Encoder-Decoder Network
• Input-to-Output Gate to Improve RNN Language Models
• Integrating User and Agent Models: A Deep Task-Oriented Dialogue System
• A Generative Model for Joint Natural Language Understanding and Generation
• Stochastic Natural Language Generation Using Dependency Information