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
Latest papers
TESS: Text-to-Text Self-Conditioned Simplex Diffusion
Diffusion models have emerged as a powerful paradigm for generation, obtaining strong performance in various continuous domains.
Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representation
Though individual translated texts are often fluent and preserve meaning, at a large scale, translated texts have statistical tendencies which distinguish them from text originally written in the language ("translationese") and can affect model performance.
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
martiansideofthemoon/ai-detection-paraphrases
•
•
NeurIPS 2023
To increase the robustness of AI-generated text detection to paraphrase attacks, we introduce a simple defense that relies on retrieving semantically-similar generations and must be maintained by a language model API provider.
kNN-BOX: A Unified Framework for Nearest Neighbor Generation
njunlp/knn-box
•
•
Augmenting the base neural model with a token-level symbolic datastore is a novel generation paradigm and has achieved promising results in machine translation (MT).
Syntactically Robust Training on Partially-Observed Data for Open Information Extraction
In this paper, we propose a syntactically robust training framework that enables models to be trained on a syntactic-abundant distribution based on diverse paraphrase generation.
Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generation
jialin-yu/latent-sequence-paraphrase
•
•
To leverage information from text pairs, we additionally introduce a novel supervised model we call dual directional learning (DDL), which is designed to integrate with our proposed VSAR model.
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.
Continuous Decomposition of Granularity for Neural Paraphrase Generation
While Transformers have had significant success in paragraph generation, they treat sentences as linear sequences of tokens and often neglect their hierarchical information.
PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation
hongyuanluke/pcc
•
•
This paper presents \textbf{PCC}: \textbf{P}araphrasing with Bottom-k Sampling and \textbf{C}yclic Learning for \textbf{C}urriculum Data Augmentation, a novel CDA framework via paraphrasing, which exploits the textual paraphrase similarity as the curriculum difficulty measure.
'John ate 5 apples' != 'John ate some apples': Self-Supervised Paraphrase Quality Detection for Algebraic Word Problems
There is a need for paraphrase scoring methods in the context of AWP to enable the training of good paraphrasers.
