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 1–50 of 172 papers

TitleStatusHype
BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingCode3
Scaling Instruction-Finetuned Language ModelsCode3
PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase IdentificationCode2
BET: A Backtranslation Approach for Easy Data Augmentation in Transformer-based Paraphrase Identification ContextCode1
Charformer: Fast Character Transformers via Gradient-based Subword TokenizationCode1
Do Multilingual Language Models Think Better in English?Code1
Factorising Meaning and Form for Intent-Preserving ParaphrasingCode1
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillationsCode1
Adversarial Semantic CollisionsCode1
What Do Questions Exactly Ask? MFAE: Duplicate Question Identification with Multi-Fusion Asking EmphasisCode1
PARADE: A New Dataset for Paraphrase Identification Requiring Computer Science Domain KnowledgeCode1
An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language ModelsCode1
Improving word mover's distance by leveraging self-attention matrixCode1
RealFormer: Transformer Likes Residual AttentionCode1
Modelling Latent Translations for Cross-Lingual TransferCode1
Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-TuningCode1
Entailment as Few-Shot LearnerCode1
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized OptimizationCode1
XLNet: Generalized Autoregressive Pretraining for Language UnderstandingCode1
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and LanguageCode1
FNet: Mixing Tokens with Fourier TransformsCode1
Improving Paraphrase Detection with the Adversarial Paraphrasing TaskCode1
NMTScore: A Multilingual Analysis of Translation-based Text Similarity MeasuresCode1
TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding LearningCode1
Self-Explaining Structures Improve NLP ModelsCode1
An Optimal Quadratic Approach to Monolingual Paraphrase Alignment—0
An Exploration of Embeddings for Generalized Phrases—0
Better Early than Late: Fusing Topics with Word Embeddings for Neural Question Paraphrase Identification—0
BnPC: A Corpus for Paraphrase Detection in Bangla—0
Bridging the Gap between Relevance Matching and Semantic Matching for Short Text Similarity Modeling—0
How much pretraining data do language models need to learn syntax?—0
Improving Large-scale Paraphrase Acquisition and Generation—0
AMRITA\_CEN@SemEval-2015: Paraphrase Detection for Twitter using Unsupervised Feature Learning with Recursive Autoencoders—0
Discriminative Improvements to Distributional Sentence Similarity—0
Balanced Adversarial Training: Balancing Tradeoffs Between Oversensitivity and Undersensitivity in NLP Models—0
A Cross-Sentence Latent Variable Model for Semi-Supervised Text Sequence Matching—0
HLTC-HKUST: A Neural Network Paraphrase Classifier using Translation Metrics, Semantic Roles and Lexical Similarity Features—0
AWE: Asymmetric Word Embedding for Textual Entailment—0
Cross-Lingual Adaptation Using Universal Dependencies—0
A Unified Kernel Approach for Learning Typed Sentence Rewritings—0
Explaining Predictive Uncertainty by Looking Back at Model Explanations—0
Co-Stack Residual Affinity Networks with Multi-level Attention Refinement for Matching Text Sequences—0
Exploiting Sentence Similarities for Better Alignments—0
Cross-lingual paraphrase identification—0
A Continuously Growing Dataset of Sentential Paraphrases—0
Deep Learning of Binary and Gradient Judgements for Semantic Paraphrase—0
Contextualized Embeddings based Convolutional Neural Networks for Duplicate Question Identification—0
Experiments on Paraphrase Identification Using Quora Question Pairs Dataset—0
Discriminative Phrase Embedding for Paraphrase Identification—0
FBK-HLT: An Effective System for Paraphrase Identification and Semantic Similarity in Twitter—0
Show:102550
← PrevPage 1 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