Context-aware Natural Language Generation with Recurrent Neural Networks

Abstract

This paper studied generating natural languages at particular contexts or situations. We proposed two novel approaches which encode the contexts into a continuous semantic representation and then decode the semantic representation into text sequences with recurrent neural networks. During decoding, the context information are attended through a gating mechanism, addressing the problem of long-range dependency caused by lengthy sequences. We evaluate the effectiveness of the proposed approaches on user review data, in which rich contexts are available and two informative contexts, sentiments and products, are selected for evaluation. Experiments show that the fake reviews generated by our approaches are very natural. Results of fake review detection with human judges show that more than 50\% of the fake reviews are misclassified as the real reviews, and more than 90\% are misclassified by existing state-of-the-art fake review detection algorithm.

References in corpus (7)

• Neural Machine Translation by Jointly Learning to Align and Translate
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Visualizing and Understanding Recurrent Networks
• Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
• A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
• Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking
• Larger-Context Language Modelling

Cited by in corpus (23)

• Explainable Outfit Recommendation with Joint Outfit Matching and Comment Generation
• Generate Natural Language Explanations for Recommendation
• Knowledge-Enhanced Personalized Review Generation with Capsule Graph Neural Network
• Neural Language Generation: Formulation, Methods, and Evaluation
• Automatic Article Commenting: the Task and Dataset
• Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation
• Improving Explainable Recommendations with Synthetic Reviews
• Conditional Text Generation for Harmonious Human-Machine Interaction
• Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation
• Contextual Text Style Transfer
• TextBox: A Unified, Modularized, and Extensible Framework for Text Generation
• Low-Rank RNN Adaptation for Context-Aware Language Modeling
• Assessing the Stylistic Properties of Neurally Generated Text in Authorship Attribution
• Improving Context Aware Language Models
• Automatic Generation of Natural Language Explanations
• Towards Controllable and Personalized Review Generation
• Read, Attend and Comment: A Deep Architecture for Automatic News Comment Generation
• Hierarchical Aspect-guided Explanation Generation for Explainable Recommendation
• A Hierarchical Attention Based Seq2seq Model for Chinese Lyrics Generation
• Adversarial Decomposition of Text Representation
• SAM: Semantic Attribute Modulation for Language Modeling and Style Variation
• Neural Task Planning with And-Or Graph Representations
• AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions