Papers with Code 아카이브
Paraphrase Identification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 11
- 보존된 평가 기록
- 44
The goal of Paraphrase Identification is to determine whether a pair of sentences have the same meaning.
Source: Adversarial Examples with Difficult Common Words for Paraphrase Identification
Image source: On Paraphrase Identification Corpora
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Improving Paraphrase Detection with the Adversarial Paraphrasing Task
Factorising Meaning and Form for Intent-Preserving Paraphrasing
FNet: Mixing Tokens with Fourier Transforms
Entailment as Few-Shot Learner
TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning
Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks
Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning
RealFormer: Transformer Likes Residual Attention
Self-Explaining Structures Improve NLP Models
Adversarial Semantic Collisions
Inducing Alignment Structure with Gated Graph Attention Networks for Sentence Matching
PARADE: A New Dataset for Paraphrase Identification Requiring Computer Science Domain Knowledge
BET: A Backtranslation Approach for Easy Data Augmentation in Transformer-based Paraphrase Identification Context
Pay Attention when Required
Better Early than Late: Fusing Topics with Word Embeddings for Neural Question Paraphrase Identification
An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models
Experiments on Paraphrase Identification Using Quora Question Pairs Dataset
Pointwise Paraphrase Appraisal is Potentially Problematic
Cross-Lingual Adaptation Using Universal Dependencies
TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding
Matching Text with Deep Mutual Information Estimation
Multi-task Sentence Encoding Model for Semantic Retrieval in Question Answering Systems
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization
Dice Loss for Data-imbalanced NLP Tasks
Sentence Embeddings for Russian NLU
TinyBERT: Distilling BERT for Natural Language Understanding
Robustness to Modification with Shared Words in Paraphrase Identification
Transfer Fine-Tuning: A BERT Case Study
PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification
StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding
Simple and Effective Text Matching with Richer Alignment Features
SpanBERT: Improving Pre-training by Representing and Predicting Spans
XLNet: Generalized Autoregressive Pretraining for Language Understanding
A Cross-Sentence Latent Variable Model for Semi-Supervised Text Sequence Matching
Unsupervised Paraphrasing without Translation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.