Papers with Code 아카이브
Paraphrase Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 3
- 보존된 평가 기록
- 5
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
A Large-Scale Benchmark for Vietnamese Sentence Paraphrases
SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation
Learning to Adapt to Low-Resource Paraphrase Generation
Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
Multi-Attribute Linguistic Tuning for Controlled Paraphrase Generation
Retrieve, Generate, Evaluate: A Case Study for Medical Paraphrases Generation with Small Language Models
Analyzing Persuasive Strategies in Meme Texts: A Fusion of Language Models with Paraphrase Enrichment
Action Controlled Paraphrasing
Parameter Efficient Diverse Paraphrase Generation Using Sequence-Level Knowledge Distillation
ParaFusion: A Large-Scale LLM-Driven English Paraphrase Dataset Infused with High-Quality Lexical and Syntactic Diversity
Improved Paraphrase Generation via Controllable Latent Diffusion
SLPL SHROOM at SemEval2024 Task 06: A comprehensive study on models ability to detect hallucination
SemEval-2024 Shared Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes
Fine-tuning CLIP Text Encoders with Two-step Paraphrasing
Neural Machine Translation for Malayalam Paraphrase Generation
LAMPAT: Low-Rank Adaption for Multilingual Paraphrasing Using Adversarial Training
Vector-Quantized Prompt Learning for Paraphrase Generation
Paraphrase Types for Generation and Detection
A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase Generation
Contextual Data Augmentation for Task-Oriented Dialog Systems
Automatic and Human-AI Interactive Text Generation
Multilingual Lexical Simplification via Paraphrase Generation
Explicit Syntactic Guidance for Neural Text Generation
Emotion and Sentiment Guided Paraphrasing
ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation
Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing
PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation
ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness
CoEdIT: Text Editing by Task-Specific Instruction Tuning
TESS: Text-to-Text Self-Conditioned Simplex Diffusion
Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representation
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
kNN-BOX: A Unified Framework for Nearest Neighbor Generation
Coherence and Diversity through Noise: Self-Supervised Paraphrase Generation via Structure-Aware Denoising
Syntactically Robust Training on Partially-Observed Data for Open Information Extraction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.