* new chunk_eval (#5138)

* new chunk_eval

* np first

* fix lac bug (#5190)

fix lac bug (#5190)

* add peoplesner, fix msraner (#5183)

add peoplesner, fix msraner (#5183)

* fix doc  for the paddlenlp version

* fix doc

* fix version bug

* update __init__

* solve conflicts

* update couplet readme

* update __init__

* fix readme version info

* modify readme

* modify readme

* modify readme

* modify readme

modify ernie_gen README (#5090)

* update __init__

* update vae readme

* update __init__

* update couplet api usage, delete useless import

* update seq2seq readme

* update seq2seq readme path

* add ernie_gen

* optimize ernie_gen

* optimize ernie_gen

* optimize ernie_gen code

* fix crf bug

* add ernie_gen __init__.py

* modify nlp version

* fix ernie_gen predict

* optimize doc

* add ernie_gen

* optimize ernie_gen

* optimize ernie_gen

* optimize ernie_gen code

* fix crf bug

* add ernie_gen __init__.py

* modify nlp version

* fix ernie_gen predict

add ernie_gen for the dygraph mode

* 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

* fix translation.py bugs

* delete useless comments

* set couplet download root None

* 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