From 894a0e692baeb6cc076b24bb766a7ff64d6231bf Mon Sep 17 00:00:00 2001 From: Xiaoyao Xi <24541791+xixiaoyao@users.noreply.github.com> Date: Wed, 12 Feb 2020 12:17:12 +0800 Subject: [PATCH] Update README.md --- README.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 90d31f7..df49cd1 100644 --- a/README.md +++ b/README.md @@ -112,7 +112,7 @@ You can easily re-produce following competitive results with minor codes, which -## Package Overview +## Overview

Sample @@ -121,6 +121,10 @@ You can easily re-produce following competitive results with minor codes, which

+PaddlePALM is a well-designed high-level NLP framework. You can efficiently achieve **supervised learning, unsupervised/self-supervised learning, multi-task learning and transfer learning** with minor codes based on PaddlePALM. There are three layers in PaddlePALM architecture, i.e., component layer, trainer layer and high-level trainer layer from bottom to top. + +In component layer, PaddlePALM supplies 7 **decoupled** components to achieve a NLP task. Each component contains rich `pre-defined Classes` and a `Base Class`. Pre-defined classes are aiming at typical NLP tasks, and the base class is to help users develop a new Class (based on pre-defined ones or from the base). + | module | illustration | | - | - | | **paddlepalm** | an open source NLP pretraining and multitask learning framework, built on paddlepaddle. | -- GitLab