Conditional Text Generation for Harmonious Human-Machine Interaction
arXiv:1909.03409
Abstract
In recent years, with the development of deep learning, text generation technology has undergone great changes and provided many kinds of services for human beings, such as restaurant reservation and daily communication. The automatically generated text is becoming more and more fluent so researchers begin to consider more anthropomorphic text generation technology, that is the conditional text generation, including emotional text generation, personalized text generation, and so on. Conditional Text Generation (CTG) has thus become a research hotspot. As a promising research field, we find that many efforts have been paid to exploring it. Therefore, we aim to give a comprehensive review of the new research trends of CTG. We first summary several key techniques and illustrate the technical evolution route in the field of neural text generation, based on the concept model of CTG. We further make an investigation of existing CTG fields and propose several general learning models for CTG. Finally, we discuss the open issues and promising research directions of CTG.
arXiv commentAccepted by the ACM Transactions on Intelligent Systems and Technology (TIST)
References in corpus (41)
- Distributed Representations of Words and Phrases and their Compositionality
- Sequence to Sequence Learning with Neural Networks
- Semi-Supervised Classification with Graph Convolutional Networks
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Language Models are Few-Shot Learners
- Teaching Machines to Read and Comprehend
- A Neural Conversational Model
- VQA: Visual Question Answering
- CTRL: A Conditional Transformer Language Model for Controllable Generation
- Wizard of Wikipedia: Knowledge-Powered Conversational agents
- MASS: Masked Sequence to Sequence Pre-training for Language Generation
- Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
- Explain Images with Multimodal Recurrent Neural Networks
- Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs
- Topic Aware Neural Response Generation
- A Simple, Fast Diverse Decoding Algorithm for Neural Generation
- Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
- Hierarchical Recurrent Attention Network for Response Generation
- DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
- Personalized Dialogue Generation with Diversified Traits
- EmotionLines: An Emotion Corpus of Multi-Party Conversations
- Low-Resource Knowledge-Grounded Dialogue Generation
- Context-aware Natural Language Generation with Recurrent Neural Networks
- Multi-Task Learning for Speaker-Role Adaptation in Neural Conversation Models
- Topic-Guided Variational Autoencoders for Text Generation
- Training Millions of Personalized Dialogue Agents
- Toward Diverse Text Generation with Inverse Reinforcement Learning
- Towards a Continuous Knowledge Learning Engine for Chatbots
- Encoder-Agnostic Adaptation for Conditional Language Generation
- An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
- Domain Aware Neural Dialog System
- Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training
- Reinforcement Learning Based Emotional Editing Constraint Conversation Generation
- CoCon: A Self-Supervised Approach for Controlled Text Generation
- Augmenting Neural Machine Translation with Knowledge Graphs
- Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation
- Steering Output Style and Topic in Neural Response Generation
- Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space
- POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training
- ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation