中文生成式预训练模型

Overview

T5 PEGASUS

中文生成式预训练模型,以mT5为基础架构和初始权重,通过类似PEGASUS的方式进行预训练。

详情可见:https://kexue.fm/archives/8209

Tokenizer

我们将T5 PEGASUS的Tokenizer换成了BERT的Tokenizer,它对中文更加友好。同时,我们重新整理了一版词表,使得里边的字、词都更加完善,目前的vocab.txt共包含5万个token,真正覆盖了中文的常用字、词。

预训练任务

预训练任务模仿了PEGASUS的摘要式预训练。具体来说,假设一个文档有n个句子,我们从中挑出大约n/4个句子(可以不连续),使得这n/4个句子拼起来的文本,跟剩下的3n/4个句子拼起来的文本,最长公共子序列尽可能长,然后我们将3n/4个句子拼起来的文本视为原文,n/4个句子拼起来的文本视为摘要,通过这样的方式构成一个“(原文, 摘要)”的伪摘要数据对。

模型下载

目前开源的T5 PEGASUS是base版,总参数量为2.75亿,训练时最大长度为512,batch_size为96,学习率为10-4,使用6张3090训练了100万步,训练时间约13天,数据是30多G的精处理通用语料,训练acc约47%,训练loss约2.97。模型使用bert4keras进行编写、训练和测试。

运行环境:tensorflow 1.15 + keras 2.3.1 + bert4keras 0.10.0

链接: https://pan.baidu.com/s/1lQ9Dt9wZDO3IgiCL9tP-Ug 提取码: 3sfn

部分评测

摘要生成效果:

小样本学习:

如何引用

Bibtex:

@techreport{zhuiyit5pegasus,
  title={T5 PEGASUS - ZhuiyiAI},
  author={Jianlin Su},
  year={2021},
  url="https://github.com/ZhuiyiTechnology/t5-pegasus",
}

联系我们

邮箱:[email protected] 追一科技:https://zhuiyi.ai

Owner
Zhuiyi Technology is a leading enterprise intelligent service AI company in China. We focus on deep learning and NLP.
Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision

Deeply Supervised, Layer-wise Prediction-aware (DSLP) Transformer for Non-autoregressive Neural Machine Translation

Chenyang Huang 37 Jan 04, 2023
Translation for Trilium Notes. Trilium Notes 中文版.

Trilium Translation 中文说明 This repo provides a translation for the awesome Trilium Notes. Currently, I have translated Trilium Notes into Chinese. Test

743 Jan 08, 2023
BERTopic is a topic modeling technique that leverages 🤗 transformers and c-TF-IDF to create dense clusters allowing for easily interpretable topics whilst keeping important words in the topic descriptions

BERTopic BERTopic is a topic modeling technique that leverages 🤗 transformers and c-TF-IDF to create dense clusters allowing for easily interpretable

Maarten Grootendorst 3.6k Jan 07, 2023
vits chinese, tts chinese, tts mandarin

vits chinese, tts chinese, tts mandarin 史上训练最简单,音质最好的语音合成系统

AmorTX 12 Dec 14, 2022
Coreference resolution for English, French, German and Polish, optimised for limited training data and easily extensible for further languages

Coreferee Author: Richard Paul Hudson, Explosion AI 1. Introduction 1.1 The basic idea 1.2 Getting started 1.2.1 English 1.2.2 French 1.2.3 German 1.2

Explosion 70 Dec 12, 2022
Ongoing research training transformer language models at scale, including: BERT & GPT-2

Megatron (1 and 2) is a large, powerful transformer developed by the Applied Deep Learning Research team at NVIDIA.

NVIDIA Corporation 3.5k Dec 30, 2022
A simple Flask site that allows users to create, update, and delete posts in a database, as well as perform basic NLP tasks on the posts.

A simple Flask site that allows users to create, update, and delete posts in a database, as well as perform basic NLP tasks on the posts.

Ian 1 Jan 15, 2022
Code for our ACL 2021 paper - ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

ConSERT Code for our ACL 2021 paper - ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer Requirements torch==1.6.0

Yan Yuanmeng 478 Dec 25, 2022
DziriBERT: a Pre-trained Language Model for the Algerian Dialect

DziriBERT is the first Transformer-based Language Model that has been pre-trained specifically for the Algerian Dialect.

117 Jan 07, 2023
ByT5: Towards a token-free future with pre-trained byte-to-byte models

ByT5: Towards a token-free future with pre-trained byte-to-byte models ByT5 is a tokenizer-free extension of the mT5 model. Instead of using a subword

Google Research 409 Jan 06, 2023
This is Assignment1 code for the Web Data Processing System.

This is a Python program to Entity Linking by processing WARC files. We recognize entities from web pages and link them to a Knowledge Base(Wikidata).

3 Dec 04, 2022
Fake news detector filters - Smart filter project allow to classify the quality of information and web pages

fake-news-detector-1.0 Lists, lists and more lists... Spam filter list, quality keyword list, stoplist list, top-domains urls list, news agencies webs

Memo Sim 1 Jan 04, 2022
Code for Findings of ACL 2022 Paper "Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors"

SWRM Code for Findings of ACL 2022 Paper "Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors" Clone Clone th

14 Jan 03, 2023
Awesome-NLP-Research (ANLP)

Awesome-NLP-Research (ANLP)

Language, Information, and Learning at Yale 72 Dec 19, 2022
Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention

Sinkhorn Transformer This is a reproduction of the work outlined in Sparse Sinkhorn Attention, with additional enhancements. It includes a parameteriz

Phil Wang 217 Nov 25, 2022
Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration

Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration This is the official repository for the EMNLP 2021 long pa

70 Dec 11, 2022
Korean Sentence Embedding Repository

Korean-Sentence-Embedding 🍭 Korean sentence embedding repository. You can download the pre-trained models and inference right away, also it provides

80 Jan 02, 2023
An end to end ASR Transformer model training repo

END TO END ASR TRANSFORMER 本项目基于transformer 6*encoder+6*decoder的基本结构构造的端到端的语音识别系统 Model Instructions 1.数据准备: 自行下载数据,遵循文件结构如下: ├── data │ ├── train │

旷视天元 MegEngine 10 Jul 19, 2022
Application to help find best train itinerary, uses speech to text, has a spam filter to segregate invalid inputs, NLP and Pathfinding algos.

T-IAI-901-MSC2022 - GROUP 18 Gestion de projet Notre travail a été organisé et réparti dans un Trello. https://trello.com/b/X3s2fpPJ/ia-projet Install

1 Feb 05, 2022