Conditional Text Generation for Harmonious Human-Machine Interaction

TL;DR

This paper reviews recent advances in conditional text generation, highlighting key techniques, research trends, and future directions in creating more human-like, emotionally aware, and personalized AI-generated text.

Contribution

It provides a comprehensive overview of neural-based CTG methods, summarizes key techniques, and discusses open challenges and future research directions.

Findings

Summarizes key techniques and evolution in neural text generation.

Proposes general learning models for CTG.

Discusses open issues and promising research directions.

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.