Paraphrase Generation
68 papers with code • 3 benchmarks • 16 datasets
Paraphrase Generation involves transforming a natural language sentence to a new sentence, that has the same semantic meaning but a different syntactic or lexical surface form.
Datasets
MS COCO
MSCOCO
Quora Question Pairs
PARANMT-50M
Duolingo STAPLE Shared Task
StyleKQC
Most implemented papers
How Large Language Models are Transforming Machine-Paraphrased Plagiarism
jpwahle/emnlp22-transforming
•
•
The recent success of large language models for text generation poses a severe threat to academic integrity, as plagiarists can generate realistic paraphrases indistinguishable from original work.
Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator
dev-chauhan/PQG-pytorch
•
•
COLING 2018
One way to ensure this is by adding constraints for true paraphrase embeddings to be close and unrelated paraphrase candidate sentence embeddings to be far.
Paraphrase Generation with Latent Bag of Words
FranxYao/Deep-Generative-Models-for-Natural-Language-Processing
•
•
NeurIPS 2019
Inspired by variational autoencoders with discrete latent structures, in this work, we propose a latent bag of words (BOW) model for paraphrase generation.
Neural Syntactic Preordering for Controlled Paraphrase Generation
tagoyal/sow-reap-paraphrasing
•
•
ACL 2020
Paraphrasing natural language sentences is a multifaceted process: it might involve replacing individual words or short phrases, local rearrangement of content, or high-level restructuring like topicalization or passivization.
Syntax-guided Controlled Generation of Paraphrases
malllabiisc/SGCP
•
•
TACL 2020
In these methods, syntactic-guidance is sourced from a separate exemplar sentence.
ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness
kinit-sk/crowd-vs-gpt-intent-class
•
•
The emergence of generative large language models (LLMs) raises the question: what will be its impact on crowdsourcing?
SLPL SHROOM at SemEval2024 Task 06: A comprehensive study on models ability to detect hallucination
sharif-slpl/se-2024-task-06-shroom
•
•
Language models, particularly generative models, are susceptible to hallucinations, generating outputs that contradict factual knowledge or the source text.
Neural Paraphrase Generation with Stacked Residual LSTM Networks
pushpendughosh/Stock-market-forecasting
•
•
COLING 2016
To the best of our knowledge, this work is the first to explore deep learning models for paraphrase generation.
A Deep Generative Framework for Paraphrase Generation
arvind385801/paraphrasegen
•
•
In this paper, we address the problem of generating paraphrases automatically.
