L-Zhe/CoRPG
Code for paper Document-Level Paraphrase Generation with Sentence Rewriting and Reordering by Zhe Lin, Yitao Cai and Xiaojun Wan. This paper is accepted by Findings of EMNLP'21.
This project helps natural language processing researchers generate alternative versions of entire documents while maintaining meaning and logical flow. You provide an original document, and it outputs a rephrased version where sentences might be rewritten or reordered. It is designed for those studying or working with advanced text generation.
No commits in the last 6 months.
Use this if you are a researcher in natural language processing (NLP) and need to generate different document-level paraphrases for text analysis or model training.
Not ideal if you need a simple tool for basic sentence paraphrasing or if your documents are longer than five sentences without code modifications.
Stars
26
Forks
5
Language
Python
License
MIT
Category
Last pushed
Nov 10, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/L-Zhe/CoRPG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
nlpcloud/nlpcloud-python
NLP Cloud serves high performance pre-trained or custom models for NER, sentiment-analysis,...
princeton-nlp/NLProofS
EMNLP 2022: Generating Natural Language Proofs with Verifier-Guided Search...
ysymyth/ec-nl
[ICLR 2022] Linking Emergent and Natural Languages via Corpus Transfer
IBM/regen
official code for EMNLP21 paper
AndyChiangSH/CDGP
Code for Findings of EMNLP 2022 short paper "CDGP: Automatic Cloze Distractor Generation based...