Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking
arXiv:1508.01755
Abstract
The natural language generation (NLG) component of a spoken dialogue system (SDS) usually needs a substantial amount of handcrafting or a well-labeled dataset to be trained on. These limitations add significantly to development costs and make cross-domain, multi-lingual dialogue systems intractable. Moreover, human languages are context-aware. The most natural response should be directly learned from data rather than depending on predefined syntaxes or rules. This paper presents a statistical language generator based on a joint recurrent and convolutional neural network structure which can be trained on dialogue act-utterance pairs without any semantic alignments or predefined grammar trees. Objective metrics suggest that this new model outperforms previous methods under the same experimental conditions. Results of an evaluation by human judges indicate that it produces not only high quality but linguistically varied utterances which are preferred compared to n-gram and rule-based systems.
To be appear in SigDial 2015
References in corpus (2)
Cited by in corpus (30)
- Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
- A Survey of Available Corpora for Building Data-Driven Dialogue Systems
- A Network-based End-to-End Trainable Task-oriented Dialogue System
- Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
- Attention with Intention for a Neural Network Conversation Model
- Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
- Context-aware Natural Language Generation with Recurrent Neural Networks
- A Context-aware Natural Language Generator for Dialogue Systems
- Neural Generative Question Answering
- Few-shot Natural Language Generation for Task-Oriented Dialog
- Backward and Forward Language Modeling for Constrained Sentence Generation
- Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data
- Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models
- Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information
- Neural Personalized Response Generation as Domain Adaptation
- Beam Search with Bidirectional Strategies for Neural Response Generation
- Deep Active Learning for Dialogue Generation
- A framework for anomaly detection using language modeling, and its applications to finance
- AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models
- Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding
- Contextual Text Style Transfer
- Towards Unsupervised Language Understanding and Generation by Joint Dual Learning
- Continual Learning for Natural Language Generation in Task-oriented Dialog Systems
- How to Build User Simulators to Train RL-based Dialog Systems
- Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks
- HUMBO: Bridging Response Generation and Facial Expression Synthesis
- Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation
- A Review of Dialogue Systems: From Trained Monkeys to Stochastic Parrots
- Hierarchical Context Enhanced Multi-Domain Dialogue System for Multi-domain Task Completion
- AGGGEN: Ordering and Aggregating while Generating