ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation

TL;DR

ProphetNet-X extends the ProphetNet pre-training framework to multiple languages and domains, achieving state-of-the-art results across diverse natural language generation tasks including summarization, question generation, dialog, and code generation.

Contribution

This work introduces ProphetNet-X, a family of large-scale pre-training models for multiple languages and tasks, with a unified structure and improved performance.

Findings

Achieved new state-of-the-art on 10 benchmarks.

Successfully extended ProphetNet to multilingual, dialog, and code generation.

Models are publicly available for diverse NLP applications.

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.