A systematic literature review on text generation using deep neural network models
In recent years, significant progress has been made in text generation. The latest text
generation models are revolutionizing the domain by generating human-like text. It has …
generation models are revolutionizing the domain by generating human-like text. It has …
Controllable Data Generation by Deep Learning: A Review
Designing and generating new data under targeted properties has been attracting various
critical applications such as molecule design, image editing and speech synthesis …
critical applications such as molecule design, image editing and speech synthesis …
[HTML][HTML] Learning towards conversational AI: A survey
Recent years have witnessed a surge of interest in the field of open-domain dialogue.
Thanks to the rapid development of social media, large dialogue corpus from the Internet …
Thanks to the rapid development of social media, large dialogue corpus from the Internet …
Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation
We analyze the behaviors of open large language models (LLMs) on the task of data-to-text
(D2T) generation, ie, generating coherent and relevant text from structured data. To avoid …
(D2T) generation, ie, generating coherent and relevant text from structured data. To avoid …
Hierarchical template transformer for fine-grained sentiment controllable generation
Existing methods for text generation usually fed the overall sentiment polarity of a product as
an input into the seq2seq model to generate a relatively fluent review. However, these …
an input into the seq2seq model to generate a relatively fluent review. However, these …
Context-aware style learning and content recovery networks for neural style transfer
L Wu, P Liu, Y Yuan, S Liu, Y Zhang - Information Processing & …, 2023 - Elsevier
Neural text transfer aims to change the style of a text sequence while keeping its original
content. Due to the lack of parallel data, unsupervised learning-based approaches have …
content. Due to the lack of parallel data, unsupervised learning-based approaches have …
Controllable data generation by deep learning: A review
Designing and generating new data under targeted properties has been attracting various
critical applications such as molecule design, image editing and speech synthesis …
critical applications such as molecule design, image editing and speech synthesis …
What makes data-to-text generation hard for pretrained language models?
Expressing natural language descriptions of structured facts or relations--data-to-text
generation (D2T)--increases the accessibility of structured knowledge repositories. Previous …
generation (D2T)--increases the accessibility of structured knowledge repositories. Previous …
Natural language generation for advertising: A survey
Natural language generation methods have emerged as effective tools to help advertisers
increase the number of online advertisements they produce. This survey entails a review of …
increase the number of online advertisements they produce. This survey entails a review of …
Recommendation with Generative Models
Generative models are a class of AI models capable of creating new instances of data by
learning and sampling from their statistical distributions. In recent years, these models have …
learning and sampling from their statistical distributions. In recent years, these models have …