* The first version of plato2. Not finished the network.

* Update decode stratage.

* Update decode stratage.

* Completed the encoder and decoder. But it will oom.

* Completed the encoder and decoder.

* backend the code.

* Only completed the network of plato2 and nsp.

* Completed the development. But the effect has not be verified.

* Add readme and remove the code about deal PY2 and PY3.

* Modify comment.

* Modify readme and add images.

* Delete the data folder.

update docs for ernie-tiny

add ernie_gen for the dygraph mode

* fix translation dataset and simplify transformer reader

update codes for paddenlp text cls example

* update seq2seq, using paddlenlp

* Using new paddlenlp API

* update seq2seqREADME

* wrap dev ds

* delete useless comments

* update predict.py

* using paddlenlp.bleu

* remove shard

* update README, using bleu perl

* delete cand

* Remove tokens that make sentences longer than max_len

* remove pdb

* remove useless code.

* update url and dataset name of vae dataset(ptb and yahoo)

* update seq2seq and vae, data and README

update the readme for the word_embedding (#5050)

* add all wiki embedding and part of baidu encyclopedia embedding.

* add embedding example

* add people_daily, weibo, sougou pretrained embedding

* add zhihu, finacial,literature embedding

* Add embedding model readme; add embedding train example and readme

* fix README example

* fix embedding doc

* add paddle.models api reference docs

* update docs

* update docs

* update docs

* tmp

* update docs

* update docs

* update docs

* update docs

* update docs

* update docs

* fix translation.py bugs

* delete useless comments

* set couplet download root None

* add paddle.models api reference docs

* update docs

* update docs

* update docs

* tmp

* update docs

* update docs

* update docs

* update docs

* update couplet readme

* update generation example

* add couplet

* simplify model code

* simplify code

* update couplet README

* add pad_token to TranslationDataset, update CoupletDataset

* update couplet url, add couplet generation example

* update TranslationDataset

* upadte classname to self in __init__

* update README.md

* add paddle.models api reference docs

* update docs

* update docs

* update docs

Co-authored-by: Nwawltor <fanzeyang0904@hotmail.com>

* add paddle.models api reference docs

* update docs

* update docs

* Add Express Example

* Add Express Data

* Add Ernie for Express Example

* add the express for the paddlenlp
Co-authored-by: Nwanghuijuan03 <wanghuijuan03@baidu.com>

* update docs

* add sbert

* add readme

* update readme

* update codes

* update lrscheduler

* minor fix

* add pre-commit

* minor fix

* Add __len__ to squad dataset

* minor fix

* Add dureader robust prototype

* dataset implement

* minor fix

* fix var name

* add dureader-yesno train script and dataset

* add readme and fix md5sum

* integrete dureader datasets

* change var names: segment to mode, root to data_file

* minor fix

* update var name

* Fix api bugs

* optimize lac

* formatted

* optimize lac

* optimize lac

* update lrscheduler

* minor fix

* add pre-commit

* minor fix

* Add __len__ to squad dataset

* minor fix

* Add dureader robust prototype

* dataset implement

* minor fix

* fix var name

* add dureader-yesno train script and dataset

* add readme and fix md5sum

* integrete dureader datasets

* change var names: segment to mode, root to data_file

* minor fix

* update var name

* update lrscheduler

* minor fix

* add pre-commit

* minor fix

* Add __len__ to squad dataset

* minor fix

* Add dureader robust prototype

* dataset implement

* minor fix

* fix var name

* add dureader-yesno train script and dataset

* add readme and fix md5sum

* integrete dureader datasets

* Unified the task name with paddle1.8

* fixed bug.

* Add TokenEmbedding

* download corpus embedding data
* load embedding data by specifying corpus name
* extend the vocab of tokenizer from corpus embedding data

* add unk token setting

* modify tokenizer

* add extend voacb

* move jieba tokenizer and rename corpus_name->embedding_name

* use bos url instead of localhost

* add log when loading data

* add token dot computation; add __repr__ of TokenEmbedding

* add color logging

* use paddlenlp.utils.log

* adjust repr

* update pretrained embedding table

* fix padding idx

* add electra pretrain and modify style of electra modeling

* add electra pretrain, modify style of electra modeling and fix problems of review

* delete predict_classifer

* modify accu to acc

* add paddlenlp.metrics.glue

* add model api

* update codes

* update codes

* update codes

* update lrscheduler

* minor fix

* add pre-commit