SOTAVerified

Paraphrase Identification

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 172 papers

TitleStatusHype
Charformer: Fast Character Transformers via Gradient-based Subword TokenizationCode1
Improving Paraphrase Detection with the Adversarial Paraphrasing TaskCode1
Factorising Meaning and Form for Intent-Preserving ParaphrasingCode1
FNet: Mixing Tokens with Fourier TransformsCode1
Entailment as Few-Shot LearnerCode1
TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding LearningCode1
Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group MasksCode0
XLA: A Robust Unsupervised Data Augmentation Framework for Cross-Lingual NLP—0
Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-TuningCode1
RealFormer: Transformer Likes Residual AttentionCode1
Self-Explaining Structures Improve NLP ModelsCode1
Adversarial Semantic CollisionsCode1
Inducing Alignment Structure with Gated Graph Attention Networks for Sentence Matching—0
PARADE: A New Dataset for Paraphrase Identification Requiring Computer Science Domain KnowledgeCode1
BET: A Backtranslation Approach for Easy Data Augmentation in Transformer-based Paraphrase Identification ContextCode1
Pay Attention when RequiredCode0
Better Early than Late: Fusing Topics with Word Embeddings for Neural Question Paraphrase Identification—0
An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language ModelsCode1
Experiments on Paraphrase Identification Using Quora Question Pairs Dataset—0
Pointwise Paraphrase Appraisal is Potentially Problematic—0
What Do Questions Exactly Ask? MFAE: Duplicate Question Identification with Multi-Fusion Asking EmphasisCode1
Cross-Lingual Adaptation Using Universal Dependencies—0
TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding—0
Matching Text with Deep Mutual Information Estimation—0
Multi-task Sentence Encoding Model for Semantic Retrieval in Question Answering Systems—0
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized OptimizationCode1
Dice Loss for Data-imbalanced NLP TasksCode0
Bridging the Gap between Relevance Matching and Semantic Matching for Short Text Similarity Modeling—0
Original Semantics-Oriented Attention and Deep Fusion Network for Sentence Matching—0
Sentence Embeddings for Russian NLUCode0
TinyBERT: Distilling BERT for Natural Language UnderstandingCode0
Robustness to Modification with Shared Words in Paraphrase Identification—0
Transfer Fine-Tuning: A BERT Case StudyCode0
A Qualitative Evaluation Framework for Paraphrase Identification—0
PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase IdentificationCode2
StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding—0
Simple and Effective Text Matching with Richer Alignment FeaturesCode0
SpanBERT: Improving Pre-training by Representing and Predicting SpansCode0
XLNet: Generalized Autoregressive Pretraining for Language UnderstandingCode1
A Cross-Sentence Latent Variable Model for Semi-Supervised Text Sequence Matching—0
Unsupervised Paraphrasing without Translation—0
Adaptation of Deep Bidirectional Multilingual Transformers for Russian LanguageCode0
ERNIE: Enhanced Language Representation with Informative EntitiesCode0
PAWS: Paraphrase Adversaries from Word ScramblingCode0
Multiresolution Graph Attention Networks for Relevance Matching—0
Multi-Task Deep Neural Networks for Natural Language UnderstandingCode0
Learning to Selectively Transfer: Reinforced Transfer Learning for Deep Text Matching—0
BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingCode3
Co-Stack Residual Affinity Networks with Multi-level Attention Refinement for Matching Text Sequences—0
Training Complex Models with Multi-Task Weak SupervisionCode0
Show:102550
← PrevPage 2 of 4Next →
All datasetsQuora Question PairsMSRPQuora Question Pairs Dev2017_test setAPIMDbPITTranslated SNLI Dataset in MarathiTURLWikiHopYelp

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1BERT-BaseDirect Intrinsic Dimension9,295—Unverified
2data2vecAccuracy92.4—Unverified
3SMART-BERTDev Accuracy91.5—Unverified
4ALICEF190.7—Unverified
5MFAEAccuracy90.54—Unverified
6RoBERTa-large 355M + Entailment as Few-shot LearnerF189.2—Unverified
7MwAN Accuracy89.12—Unverified
8DIINAccuracy89.06—Unverified
9MSEMAccuracy88.86—Unverified
10Bi-CAS-LSTMAccuracy88.6—Unverified
#ModelMetricClaimedVerifiedStatus
1FEAT2, TFKLD, SVM, Fine-grained featuresAccuracy80.41—Unverified
2NMF factorization-unigrams-TFKLDAccuracy72.75—Unverified
3SWEM-concatAccuracy71.5—Unverified
#ModelMetricClaimedVerifiedStatus
1BERT + SCH attmVal Accuracy91.42—Unverified
2BERT + SCH attnVal F1 Score88.44—Unverified
#ModelMetricClaimedVerifiedStatus
1CNN10 fold Cross validation50—Unverified
#ModelMetricClaimedVerifiedStatus
1RoBETRa baseMCC0.53—Unverified
#ModelMetricClaimedVerifiedStatus
1SplitEE-SAccuracy82.2—Unverified
#ModelMetricClaimedVerifiedStatus
1TSDAEAP69.2—Unverified
#ModelMetricClaimedVerifiedStatus
1Weighted Ensemble of TF-IDF and BERT Embeddings1:1 Accuracy82.04—Unverified
#ModelMetricClaimedVerifiedStatus
1TSDAEAP76.8—Unverified
#ModelMetricClaimedVerifiedStatus
1StructBERTRoBERTa ensembleAccuracy90.7—Unverified
#ModelMetricClaimedVerifiedStatus
1SplitEE-SAccuracy76.7—Unverified