ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation
arXiv:2104.08006
Abstract
Now, the pre-training technique is ubiquitous in natural language processing field. ProphetNet is a pre-training based natural language generation method which shows powerful performance on English text summarization and question generation tasks. In this paper, we extend ProphetNet into other domains and languages, and present the ProphetNet family pre-training models, named ProphetNet-X, where X can be English, Chinese, Multi-lingual, and so on. We pre-train a cross-lingual generation model ProphetNet-Multi, a Chinese generation model ProphetNet-Zh, two open-domain dialog generation models ProphetNet-Dialog-En and ProphetNet-Dialog-Zh. And also, we provide a PLG (Programming Language Generation) model ProphetNet-Code to show the generation performance besides NLG (Natural Language Generation) tasks. In our experiments, ProphetNet-X models achieve new state-of-the-art performance on 10 benchmarks. All the models of ProphetNet-X share the same model structure, which allows users to easily switch between different models. We make the code and models publicly available, and we will keep updating more pre-training models and finetuning scripts.
arXiv commentAccepted by ACL 2021 demo papers
References in corpus (19)
- Sequence to Sequence Learning with Neural Networks
- Language Models are Few-Shot Learners
- Teaching Machines to Read and Comprehend
- A Neural Conversational Model
- Multilingual Denoising Pre-training for Neural Machine Translation
- MASS: Masked Sequence to Sequence Pre-training for Language Generation
- CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
- CodeBERT: A Pre-Trained Model for Programming and Natural Languages
- Neural Responding Machine for Short-Text Conversation
- GraphCodeBERT: Pre-training Code Representations with Data Flow
- Text Summarization with Pretrained Encoders
- DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
- XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation
- CLUE: A Chinese Language Understanding Evaluation Benchmark
- Unified Pre-training for Program Understanding and Generation
- Global Encoding for Abstractive Summarization
- Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks
- GLGE: A New General Language Generation Evaluation Benchmark
- MATINF: A Jointly Labeled Large-Scale Dataset for Classification, Question Answering and Summarization